Mechanistic Interpretability

Ask about this topic

Recent momentum

-70%

6 papers in the last 28 days · 0.2% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Also in Mechanistic Interpretability

Neighbouring directions

Model Interpretability MethodsInterpretable Machine Learning

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-14

2 new papers

A weekly snapshot of new work published in Mechanistic Interpretability.

Period ending 2026-09-07

6 new papers

A weekly snapshot of new work published in Mechanistic Interpretability.

154 papers

Latest in Mechanistic Interpretability

Open your feed →
CardsList

  1. On the Recall Scaling Laws in Mamba: A Theoretical and Mechanistic Study via Hashing

    Sep 7, 2026Yuval Koren, Assaf Ben-Kish, Raja Giryes +2Associative MemoryFactual Recall

  2. Large Language Models in Resolving Contextual Knowledge Conflicts

    Sep 2, 2026Xinye Yang, Zhenyang Liu, Ruisi Li +1ConflictMechanistic Interpretability

  3. ObserverBench: Testing Mechanistic Estimates for Intervention and Control

    Sep 2, 2026Vijay ErramilliMechanistic InterpretabilityCausal Intervention

  4. S^3martCirc: Self-supervised Smart Circuit Discovery

    Sep 1, 2026Wendy Zheng, Yinhan He, Liang Wu +1Mechanistic InterpretabilityCircuits

  5. MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines

    Aug 31, 2026Alireza Bayat Makou, Emirhan Böge, Phu Gia Hoang +5Model Interpretability MethodsMechanistic Interpretability

  6. The Safety Relay in Roleplay Jailbreaks: A Component-Resolved Causal Analysis of Harm Recognition and Refusal

    Aug 31, 2026Md Mokarram Chowdhury, Ernie Chang, Yang LiJailbreaksRefusals

  7. Decoding Task Progress from VLA Representations

    Aug 13, 2026Atiksh Bhardwaj, Edward Weiyi Duan, Prithwish Dan +2Vision-Language-ActionVisuomotor Policy

  8. Perturbation-based Regional Interpretability through Subtraction Mapping (PRISM): naming-error dissociations in language models and post-stroke aphasia

    Aug 13, 2026Xiang Guan, Roger D. Newman-Norlund, Yong Yang +8Dysarthric SpeechLinguistics

  9. Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence

    Aug 12, 2026Mengru Wang, Junfeng Fang, Shuofei Qiao +16Artificial Intelligence SafetyArtificial Intelligence Scientists

  10. Causal Structure is Inducible but Functionally Decoupled: The Routing/Readout Boundary of a Typed Mechanism Library

    Aug 12, 2026Xining XunCausal Structure and ReasoningMechanistic Interpretability

  11. From Interpretability to Control: Insights from Six Years of the TrustNLP Workshop

    Aug 11, 2026Rahul Gupta, Abhinav Mohanty, Anaelia Ovalle +10Large Language Model ReliabilityModel Interpretability Methods

  12. Measuring Semantic Abstractness of SAE Features via Nonlocality

    Aug 11, 2026Chuqiao Lin, Shivaji Sondhi, Xiao-Liang QiSparse AutoencodersMechanistic Interpretability

  13. Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability

    Aug 10, 2026Ashim Dhor, Pin-Yu ChenMechanistic InterpretabilityModel Interpretability Methods

  14. Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models

    Aug 10, 2026Kevin MurphyAgentic DiscoveryStructural Causal Model

  15. Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways

    Aug 10, 2026Shuyi Miao, Wangjie Qiu, Pengyang Shao +4Multilingual SafetyLarge Language Model Alignment

  16. Finding Usable Weight Mechanisms with Tiled SVD

    Aug 7, 2026Ash Manvi, Samreena TajreenModel WeightsSingular Value Decomposition

  17. MI-MIDI: Mechanistic Interpretability of Text-to-MIDI Generation Models via Probing, Lenses and Steering

    Aug 6, 2026Jakub Poćwiardowski, Mateusz ModrzejewskiGenerative Music ModelsMusic Generation

  18. Sparse Weight Decomposition for Efficient Circuit Extraction

    Aug 4, 2026Chuanhao Yan, Xuhan Huang, Yawen Duan +4Model WeightsCircuits

  19. DiffuseAgent-MI: Distributionally-Grounded,Tool-Integrated Self-Evolving Agents for Faithful Visual Reasoning

    Aug 1, 2026An Lanji, Dawei Liu, Jin Li +3Visual ReasoningMechanistic Interpretability

  20. Emergent Latent-State Computation under Stochastic Volatility

    Jul 28, 2026Xiaoyu Huang, Lulu WangIntermediate Latent StatesLatent States

  21. Do LLMs Know Their Vulnerable Scenarios?

    Jul 26, 2026Ziheng Peng, Huiqi Deng, Haoran Jing +5Large Language Model SafetyVulnerable Code

  22. Continuous surrogates versus threshold Boolean networks for modeling Arabidopsis ISR gene regulation

    Jul 25, 2026Gonzalo A. RuzRegulatory NetworksSurrogate Modeling

  23. Through the Bottleneck: How Multi-head Latent Attention Separates Content from Position in Language Models

    Jul 25, 2026Dhruvil S, Fenil Sojitra, Ravirajsinh ChauhanMulti-Head AttentionDeepseek-R1

  24. Toward Mechanistic Interpretability of an AI Foundation Model Fine-Tuned for Atmospheric Chemistry

    Jul 22, 2026Jason Y. Hu, Ivan Higuera-Mendieta, Patrick Obin Sturm +1Atmospheric CorrectionWireless Foundation Models

  25. Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model

    Jul 22, 2026Markus J. BuehlerMaterials ScienceMechanistic Interpretability

  26. Measuring Monosemanticity in Sparse Autoencoders via Latent Activation Coherence

    Jul 20, 2026Katarzyna Filus, Sebastian PokucińskiSparse AutoencodersMechanistic Interpretability

  27. Are Arithmetic Heuristic Neurons Form-Invariant? A Mechanistic Analysis of Symbols, Text, and Code in LLMs

    Jul 18, 2026Sharath Naganna, Tanvir Ahmed Sijan, Uddipta KalitaLarge Language Models FailMechanistic Interpretability

  28. Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control

    Jul 16, 2026Jihoon Hong, Julian Skifstad, Qiyue Dai +2Linear Activation SteeringWorld Models

  29. Transcoders for Investigating Deception in Language Models

    Jul 16, 2026Darius Lim, Nathan Leow, Xin Wei ChiaDeceptionMechanistic Interpretability

  30. Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions

    Jul 15, 2026Zachary IzzoNext-Token PredictionTraining Data

  31. From Observation to Insight: Mechanistic World Models and the Quest for Autonomous Discovery

    Jul 14, 2026Ingmar Posner, Anson Lei, Bernhard SchölkopfScientific DiscoveryMechanistic Interpretability

  32. Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias

    Jul 13, 2026Zixiang Xu, Sixian Li, Huaxing Liu +4JudgesMechanistic Interpretability

  33. Cross-seed explainability using Procrustes-conditioned Joint End-to-end Top-K Sparse Autoencoders

    Jul 9, 2026Bendegúz Váradi, Zoltán KmettyImproving Sparse AutoencodersSparse Autoencoders

  34. Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability

    Jul 9, 2026Amir AsiaeeModel Interpretability MethodsMechanistic Interpretability

  35. Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs

    Jul 8, 2026Anupam Wagle, Ifrat Ikhtear Uddin, Chaowei Zhang +1Large Language Model JailbreaksAdversarial Prompts

  36. Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning

    Jul 8, 2026Pranav Sawant, Jakub KrejčíMechanistic InterpretabilityExplainable Artificial Intelligence

  37. Latent Programming Horizons in Coding Agents

    Jul 6, 2026André Silva, Han Tu, Martin MonperrusCoding AgentsLarge Language Model Agents

  38. Individual Parameters in Weight-Sparse Transformers Appear Interpretable

    Jul 3, 2026Arnau Marin-Llobet, Stefan HeimersheimMechanistic InterpretabilityModel Weights

  39. Towards Robustness against Typographic Attack with Training-free Concept Localization

    Jul 2, 2026Bohan Liu, Wenqian Ye, Guangzhi Xiong +3Contrastive Language-Image Pre-TrainingVision Transformer

  40. Conditional Co-Ablation: Recovering Self-Repair Backups in Transformer Circuits

    Jul 2, 2026Zhiren Gong, Zihao Zeng, Chau Yuen +1AblationTransformer Variant

  41. Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability

    Jul 2, 2026Rodrigo Mendoza-SmithImproving Sparse AutoencodersSparse Autoencoders

  42. Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse Autoencoders

    Jul 1, 2026Zihao Qi, Christopher EarlsQuantum LearningMany-Body Physics

  43. Representation as a Bottleneck for Mechanistic Interpretability: The Manifestation Unit Protocol

    Jun 30, 2026Hussein Chouman, Wataru Sasaki, Tomokazu Matsui +2Mechanistic InterpretabilityModel Interpretability Methods

  44. Surrogate Fidelity: When Can Open LLMs Explain Closed Ones?

    Jun 30, 2026Philippe Chlenski, Zachariah Carmichael, Ayush Warikoo +5Mechanistic InterpretabilityAttribution Methods

  45. Symbolic Mechanistic Data Attribution: Tracing Training Influence to Learned Behavioral Policies

    Jun 28, 2026Reza Habibi, Darian Lee, Magy Seif El-NasrFeature AttributionMechanistic Interpretability

  46. Mechanistic Personality Analysis of LLMs Steering Personality via Latent Feature Interventions

    Jun 27, 2026David Courtis, Ting HuPersonalityLarge Language Model Personalization

  47. Can LLMs Judge Better Than They Generate? Evaluating Task Asymmetry, Mechanistic Interpretability and Transferability for In-Context QA

    Jun 26, 2026Sambaran BandyopadhyayModel Self-AssessmentIn-Context

  48. The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching

    Jun 25, 2026Sankaran Vaidyanathan, David Arbour, Aaron Mueller +2Mechanistic InterpretabilityMediation

  49. PairSAE: Mechanistic Interpretability from Pair Representations in Protein Co-Folding

    Jun 25, 2026Giosue Migliorini, Aristofanis Rontogiannis, Grigori Guitchounts +3ProteinSparse Autoencoders

  50. Batch-Invariant Spectral Intelligence for Robust and Explainable Insect Authentication

    Jun 25, 2026Majharulislam Babor, Giacomo Rossi, Annalisa Altavilla +2Non-Destructive Frying Oil Oxidation AssessmentBiodiversity Monitoring

  51. Radical AI Interpretability

    Jun 25, 2026Daniel A. Herrmann, Benjamin A. LevinsteinMechanistic InterpretabilityModel Interpretability Methods

  52. Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models

    Jun 23, 2026Cosimo Galeone, Anna Ettorre, Minsu Park +2Mechanistic InterpretabilitySteering

  53. Can Language Model Agents be Helpful Circuit Explainers in Mechanistic Interpretability?

    Jun 23, 2026Ayan Antik Khan, Harsh Kohli, Yuekun Yao +2Mechanistic InterpretabilityCircuits

  54. AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent

    Jun 21, 2026Weidi Luo, Qiming Zhang, Yihao Quan +5Large Language Model SafetyAI Safety Alignment

  55. Who Wins the Conflict? Mechanistic Interpretability of Text Bias in Audio LLMs

    Jun 17, 2026Hyebin Cho, Suho Yoo, Jaehyuk Jang +2Large Audio Language ModelsLarge Language Model Alignment

  56. Closing the Loop: PID Feedback Control for Interpretable Activation Steering in Symbolic Music Generation

    Jun 17, 2026Ioannis Prokopiou, Pantelis Vikatos, Maximos Kaliakatsos-Papakostas +2Linear Activation SteeringInference-Time Control

  57. Effects of sparsity and superposition on loss in simple autoencoders

    Jun 16, 2026Mriganka Basu Roy Chowdhury, Eric McLaughlin WeinerSuperpositionAutoencoder

  58. Scalable Circuit Learning for Interpreting Large Language Models

    Jun 15, 2026Naiyu Yin, Dennis Wei, Tian Gao +3Mechanistic InterpretabilityCircuits

  59. Demystifying Variance in Circuit Discovery of LLMs

    Jun 15, 2026Frank Zhengqing Wu, Francesco Tonin, Volkan CevherMechanistic InterpretabilityCircuits

  60. Circuit Tracing in Autoregressive Protein Language Models

    Jun 14, 2026Darin Tsui, William Deinzer, Daniel Saeedi +1Mechanistic InterpretabilityProtein Language Model