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

119 papers, page 3 of 3

101. ICML 2025The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training
102. ICML 2025To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models
103. ICML 2025Towards Global-level Mechanistic Interpretability: A Perspective of Modular Circuits of Large Language Models
104. ICML 2025Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models
105. ICML 2025Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
106. ICML 2025Validating Mechanistic Interpretations: An Axiomatic Approach
107. ICML 2025Which Attention Heads Matter for In-Context Learning?
108. ICML 2024Attention Meets Post-hoc Interpretability: A Mathematical Perspective
109. ICML 2024Autaptic Synaptic Circuit Enhances Spatio-temporal Predictive Learning of Spiking Neural Networks
110. ICML 2024From Neurons to Neutrons: A Case Study in Interpretability
111. ICML 2024Interpretability Illusions in the Generalization of Simplified Models
112. ICML 2024Local vs. Global Interpretability: A Computational Complexity Perspective
113. ICML 2024Mechanistic Neural Networks for Scientific Machine Learning
114. ICML 2024Observable Propagation: Uncovering Feature Vectors in Transformers
115. ICML 2024Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neuroscience
116. ICML 2024What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation
117. ICML 2023A Toy Model of Universality: Reverse Engineering how Networks Learn Group Operations
118. ICML 2023Mechanistic Mode Connectivity
119. ICML 2023On the Impact of Knowledge Distillation for Model Interpretability

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.