Mechanistic Interpretability papers, 2023–2026

Key findings

• Mechanistic Interpretability went from 17 papers in 2023 to 138 in 2026, roughly 8.1x in three years.
• ICML publishes the most Mechanistic Interpretability work: 119 papers from 2023 to 2026, 38% of the four-venue total.
• The fastest-growing overlap is with Deep learning · large language models: papers tagged with both rose from 1 in 2023 to 23 in 2026.
• Among the 5 topics under Interpretability, it ranks #2 by 2026 paper count; the fastest grower in the group, Feature Attribution, is up 1.9x versus 8.1x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A Mechanistic Interpretability Study of an Astronomical Foundation Model
• ICML 2026Contribution Weights: A Geometrical Analysis of Self-Attention Transformers
• ICLR 2026Circuit Insights: Towards Interpretability Beyond Activations
• CVPR 2026CIGMA Causal Information-Gain Mechanistic Attribution of Attention Heads in Vision
• NeurIPS 2025Beyond Components: Singular Vector-Based Interpretability of Transformer Circuits
• ICML 2025Algorithm Development in Neural Networks: Insights from the Streaming Parity Task
• ICLR 2025Arithmetic Without Algorithms: Language Models Solve Math with a Bag of Heuristics
• CVPR 2025Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability
• NeurIPS 2024InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques
• ICML 2024Mechanistic Neural Networks for Scientific Machine Learning
• ICLR 2024Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking
• CVPR 2024SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology
• NeurIPS 2023A Logic for Expressing Log-Precision Transformers
• ICML 2023Mechanistic Mode Connectivity
• ICLR 2023Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 Small
• NeurIPS 2026Discovering Mechanistic Models of Neural Activity: System Identification in an in Silico Zebrafish
• ICML 2026CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features
• ICLR 2026CLUE: Conflict-guided Localization for LLM Unlearning Framework
• CVPR 2026From Weights to Concepts Data-Free Interpretability of CLIP via Singular
• NeurIPS 2025Bigram Subnetworks: Mapping to Next Tokens in Transformer Language Models

All Mechanistic Interpretability papers

38 papers, page 1 of 1

1. ICLR 2025Adaptive Transformer Programs: Bridging the Gap Between Performance and Interpretability in Transformers
2. ICLR 2025Arithmetic Without Algorithms: Language Models Solve Math with a Bag of Heuristics
3. ICLR 2025Attention as a Hypernetwork
4. ICLR 2025Bilinear MLPs enable weight-based mechanistic interpretability
5. ICLR 2025Controllable Context Sensitivity and the Knob Behind It
6. ICLR 2025Density estimation with LLMs: a geometric investigation of in-context learning trajectories
7. ICLR 2025Differential learning kinetics govern the transition from memorization to generalization during in-context learning
8. ICLR 2025Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient
9. ICLR 2025Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models
10. ICLR 2025Eliminating Position Bias of Language Models: A Mechanistic Approach
11. ICLR 2025Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?
12. ICLR 2025Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation
13. ICLR 2025HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks
14. ICLR 2025Improving Instruction-Following in Language Models through Activation Steering
15. ICLR 2025Interpreting Emergent Planning in Model-Free Reinforcement Learning
16. ICLR 2025Interpreting the Second-Order Effects of Neurons in CLIP
17. ICLR 2025Linear Representations of Political Perspective Emerge in Large Language Models
18. ICLR 2025Mechanistic Permutability: Match Features Across Layers
19. ICLR 2025Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity
20. ICLR 2025Monet: Mixture of Monosemantic Experts for Transformers
21. ICLR 2025Not All Language Model Features Are One-Dimensionally Linear
22. ICLR 2025ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability
23. ICLR 2025Residual Stream Analysis with Multi-Layer SAEs
24. ICLR 2025Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words
25. ICLR 2025Revealing and Mitigating Over-Attention in Knowledge Editing
26. ICLR 2025Revisiting In-context Learning Inference Circuit in Large Language Models
27. ICLR 2025Robust LLM safeguarding via refusal feature adversarial training
28. ICLR 2025Scalable Mechanistic Neural Networks
29. ICLR 2025Sparse Autoencoders Do Not Find Canonical Units of Analysis
30. ICLR 2025Systematic Outliers in Large Language Models
31. ICLR 2025The Computational Complexity of Circuit Discovery for Inner Interpretability
32. ICLR 2025Towards a Unified and Verified Understanding of Group-Operation Networks
33. ICLR 2025Towards Interpreting Visual Information Processing in Vision-Language Models
34. ICLR 2025Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control
35. ICLR 2025Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures
36. ICLR 2025Transformers Struggle to Learn to Search
37. ICLR 2025Uncovering Latent Memories in Large Language Models
38. ICLR 2025Words in Motion: Extracting Interpretable Control Vectors for Motion Transformers

FAQ

How many Mechanistic Interpretability papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

311 in total: 17 in 2023, 49 in 2024, 107 in 2025, 138 in 2026.

How many Mechanistic Interpretability papers are at NeurIPS 2026?

NeurIPS 2026 has 16 Mechanistic Interpretability papers, versus 34 the year before.

How many Mechanistic Interpretability papers are at ICLR 2026?

ICLR 2026 has 46 Mechanistic Interpretability papers, versus 38 the year before.

How many Mechanistic Interpretability papers are at ICML 2026?

ICML 2026 has 74 Mechanistic Interpretability papers, versus 33 the year before.

How many Mechanistic Interpretability papers are at CVPR 2026?

CVPR 2026 has 2 Mechanistic Interpretability papers, versus 2 the year before.

Which conference publishes the most Mechanistic Interpretability papers?

ICML, with 119 papers from 2023 to 2026.