Mechanistic Interpretability

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

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

Weekly history

Recent digests

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

Period ending 2026-09-21

12 new papers

A weekly snapshot of new work published in Mechanistic Interpretability.

Period ending 2026-09-14

10 new papers

A weekly snapshot of new work published in Mechanistic Interpretability.

Period ending 2026-09-07

13 new papers

A weekly snapshot of new work published in Mechanistic Interpretability.

Inside this field

Focused directions

Focused topic

Model Interpretability

Within Mechanistic Interpretability

269 papersExplore

Focused topic

Mechanistic Interpretability

Within Mechanistic Interpretability

158 papersExplore

Focused topic

Interpretable Models

Within Mechanistic Interpretability

38 papersExplore

434 papers

Latest in Mechanistic Interpretability

Browse all topics →

Beyond Point Prediction: Artificial Representative Trees with Uncertainty
Sep 21, 2026Lea L. Mairhöfer, Silke Szymczak, Björn-Hergen Laabs +1Predictive Uncertainty Interpretable Models
Falling Trees: A Model Class for Interpretable Risk Prioritization
Sep 20, 2026Varun Babbar, Zachery Boner, Margo Seltzer +1Decision Trees Interpretable Models
Transferring Visual Explanations: How Cross-Architecture Knowledge Distillation Affects Model Interpretability
Sep 20, 2026Aleks Czufarow, Ihor BabinModel Interpretability Training-Free Inference Framework
Reproducing Transparent and Scrutable Recommendations: Exploring Open-Weight Models via Natural-Language User Profiles
Sep 17, 2026Noah Mamié, Laurin van den BerghRecommender Systems Profile
Flag Game: A Toy Model for Mechanistic Swarm Interpretability
Sep 16, 2026Elizabeth Pavlova, Hidenori TanakaCollective Behaviors Swarms
Using OCR Heads to Verbalize Image Semantics
Sep 16, 2026Sheridan Feucht, Benno Krojer, Sarah Wang +3Optical Character Recognition Model Interpretability
A unified framework for global and local interpretability using adaptive derivative-ordered random explanation
Sep 15, 2026Lemen Chao, Ming Lei, Anran FangModel Interpretability Feature Importance
Can We Do Interpretable NLI with Graphs Based on Atomic Propositions?
Sep 15, 2026Younes Boufouss, Luc Pommeret, Thomas Gerald +2Natural Language Inference Model Interpretability
Learned Look-Ahead Splitting Rule for CART
Sep 14, 2026Andrew Gao, Tianlin Liu, Ruichen Han +1Decision Trees Lookahead
Data storytelling meets interpretable machine learning: Decoding AI decisions for non-experts without revealing sensitive data and model details
Sep 14, 2026Lemen Chao, Zixuan Yang, Anran Fang +2Model Interpretability Experts
The Misery of Mechanistic Interpretability: A Formal Perspective
Sep 14, 2026Tobias Ladner, Matthias AlthoffMechanistic Interpretability Model Interpretability
Artificial entrepreneurial cognition: Locating and causally steering an opportunity recognition dial inside large language models (LLMs)
Sep 14, 2026Christian Fisch, Angela Altmeier, Martin Obschonka +2Artificial Intelligence Systems Mechanistic Interpretability
What Does an LLM Learn from Reinforcement Learning? A Mechanistic Interpretability Perspective with Fixed-SAE Track
Sep 14, 2026Lingheng Du, Yiming Tang, Xufeng Duan +1Sparse Autoencoder Features Mechanistic Interpretability
Data Attribution at Scale via Influence Matrix Estimation
Sep 14, 2026Yuxi Chen, Hamza Golubovic, Han Tong +2Training Data Attribution Attention-Based Models
MAxBench: A Multinomial Concept Recovery Benchmark
Sep 14, 2026Divya Appapogu, Freya Behrens, Yonatan Belinkov +1Model Interpretability
Calibrating Interpretability Instruments Before Trusting Their Verdicts
Sep 13, 2026Orion Reblitz-RichardsonModel Interpretability Correctness
XAI-Arena: Can LLMs Assess the Quality of XAI Explanations?
Sep 10, 2026Yanfei Hu Fleischhauer, Alona Zharova, Nadja Klein +1Xai Explainable Artificial Intelligence
Auditable Emergency Triage for Maternal and Newborn Care in India
Sep 10, 2026Shobhit Jagga, Aman Dalmia, Niharika Priyadarshini +7Triage Model Interpretability
An Explainable Machine Learning Framework for Predicting Blood-Brain Barrier Permeability Using Molecular Descriptors
Sep 9, 2026Fatemeh MahmoudiMolecular Property Prediction Drug Discovery
Do Reasoning Representations Help Humans Evaluate LLM Outputs?
Sep 8, 2026Jaewoo Lim, Sungbok Shin, Sanghyun HongLarge Language Model Output Model Interpretability
GraphFAS: A Distributed System for Automated Graph Feature Generation and Selection in Industrial Transaction Networks
Sep 8, 2026Yice Luo, Yun Zhu, Xi Chen +7Graph Representation Learning Fraud Detection
LLM Layers Immediately Correct Each Other
Sep 7, 2026Arjun Patrawala, Jiahai Feng, Erik Jones +1Transformer Layers Model Activations
On the Recall Scaling Laws in Mamba: A Theoretical and Mechanistic Study via Hashing
Sep 7, 2026Yuval Koren, Assaf Ben-Kish, Raja Giryes +2Dense Associative Memory Factual Recall
Unraveling the Real Working Mechanism and Inherent Flaws of GAE: A Method for Interpreting Transformer Processes from an Economic Perspective
Sep 7, 2026Yongjin Cui, Xiaohui FanExplainable Artificial Intelligence Xai
Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought Reasoning
Sep 3, 2026Kevin Du, Alexander Hoyle, Laura Ruis +1Reasoning Chain Reasoning Traces
Witnesses Explain Anomalies
Sep 3, 2026Lamine DiopAnomaly Score Anomaly
Large Language Models in Resolving Contextual Knowledge Conflicts
Sep 2, 2026Xinye Yang, Zhenyang Liu, Ruisi Li +1Conflict Large Language Model Performance
ObserverBench: Testing Mechanistic Estimates for Intervention and Control
Sep 2, 2026Vijay ErramilliMechanistic Interpretability Observation
Towards reliable multimodal disaster severity assessment through preference optimization and explainable vision-language reasoning
Sep 1, 2026Yuanjun Zhang, Fuzel Ahamed Shaik, Suvojit Acharjee +2Post-Disaster Damage Assessment Multimodal Reasoning
S^3martCirc: Self-supervised Smart Circuit Discovery
Sep 1, 2026Wendy Zheng, Yinhan He, Liang Wu +1Mechanistic Interpretability Circuits
MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines
Aug 31, 2026Alireza Bayat Makou, Emirhan Böge, Phu Gia Hoang +5Model Interpretability Mechanistic Interpretability
The Safety Relay in Roleplay Jailbreaks: A Component-Resolved Causal Analysis of Harm Recognition and Refusal
Aug 31, 2026Md Mokarram Chowdhury, Ernie Chang, Yang LiNovel Jailbreak Method Jailbreaks
Tensor Methods for Language Models: From Token Representation to Training, Adaptation, Inference, Compression, and Interpretability
Aug 31, 2026Matvei Tarasov, Salman Ahmadi-Asl, Andre L. F. de Almeida +1Large Language Model Compression Tensor Networks
RACE: Scalable Statistical Estimation of Functional Consistency in LLM Neurons
Aug 25, 2026Runyu Wang, Bo Liu, Xiaxin Zhang +6Neurophysiological Correlates Mechanistic Interpretability
TabSOM: A tabular-to-image encoding method based on self-organizing maps
Aug 13, 2026David Chushig-Muzo, María Ángeles Rodríguez de Cara, Eva Milara +3Tabular Learning Model Interpretability
Decoding Task Progress from VLA Representations
Aug 13, 2026Atiksh Bhardwaj, Edward Weiyi Duan, Prithwish Dan +2Vision-Language-Action Models Visuomotor Policy
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 +8Dissociation Dysarthric Speech
Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence
Aug 12, 2026Mengru Wang, Junfeng Fang, Shuofei Qiao +16Artificial Intelligence Safety Artificial Intelligence Scientists
HyperANFIS: Enhancing Rule Representation and Interpretability in Adaptive Neuro-Fuzzy Systems via Hyperbolic Geometry
Aug 12, 2026Haoran Pei, Zhao Su, Zetao Lin +6Hyperbolic Learning Hyperbolic Space
From Interpretability to Control: Insights from Six Years of the TrustNLP Workshop
Aug 11, 2026Rahul Gupta, Abhinav Mohanty, Anaelia Ovalle +10Trustworthy Artificial Intelligence Model Interpretability
Measuring Semantic Abstractness of SAE Features via Nonlocality
Aug 11, 2026Chuqiao Lin, Shivaji Sondhi, Xiao-Liang QiSparse Autoencoder Features Semantic Representations
Conversational versus Dashboard Explainable AI for UAV Intrusion Detection: An Empirical Study of Operator Trust and Reliance
Aug 11, 2026Cong Chi Nguyen, Trang Mai Xuan, Vu-Duc Ngo +3Unmanned Aerial Vehicle Detection Intrusion Detection
Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability
Aug 10, 2026Ashim Dhor, Pin-Yu ChenMechanistic Interpretability Model Interpretability
Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways
Aug 10, 2026Shuyi Miao, Wangjie Qiu, Pengyang Shao +4Multilingual Safety Large Language Model Safety
The Spectral Neuron
Aug 8, 2026Alex ShtoffModel Interpretability Affine
Beyond the Black Box: Interpretable Models of Human Randomisation Failures
Aug 7, 2026Ngoc Linh DaoInterpretable Models Black Box
Transformer Geometry Observatory TGO-IV: Developmental Topology Observatory
Aug 7, 2026Kaustubh Kapil, Kishor P. UplaTransformer Architectures Topological Data Analysis
Interpretable reinforcement learning with decision-tree pruning
Aug 7, 2026Mark Leon Ringer, Michel TokicDeep Reinforcement Learning Model Interpretability
Finding Usable Weight Mechanisms with Tiled SVD
Aug 7, 2026Ash Manvi, Samreena TajreenModel Weights Singular Value Decomposition
Faster Query-Key Learning Sharpens Attention in Self-Attention Models
Aug 7, 2026Rahul Vashisht, Harish G. RamaswamySoftmax Attention Model Interpretability
MI-MIDI: Mechanistic Interpretability of Text-to-MIDI Generation Models via Probing, Lenses and Steering
Aug 6, 2026Jakub Poćwiardowski, Mateusz ModrzejewskiMusic Generation Conversational Music Recommendation
Scaling Inherently Interpretable Language Models
Aug 6, 2026Guide Labs Team, Andreas Madsen, Aya Abdelsalam Ismail +7Model Interpretability Training Language Models
Sparse Weight Decomposition for Efficient Circuit Extraction
Aug 4, 2026Chuanhao Yan, Xuhan Huang, Yawen Duan +4Model Weights Transformer Architectures
xMICD: Explainable Representation of Multiple ICD Codes
Aug 2, 2026Pat Vatiwutipong, Kumkup Keeratisiwakul, Albert Phuoc Kien Van Truong +4International Classification Of Disease Codes Interpretable Models
DiffuseAgent-MI: Distributionally-Grounded,Tool-Integrated Self-Evolving Agents for Faithful Visual Reasoning
Aug 1, 2026An Lanji, Dawei Liu, Jin Li +3Visual Reasoning Mechanistic Interpretability
Persistent Convolution: A Topological Framework for AI Alignment Testing and Semantic Space Characterization
Jul 31, 2026Tyler Ashoff, Jordan RoduArtificial Intelligence Alignment Multimodal Alignment
Search Strategies for Optimal Classification and Regression Trees
Jul 30, 2026Jacobus G. M. van der Linden, Mim van den Bos, Emir DemirovićDecision Trees Object Classification
HealthCAT: An Interpretable Encoder-only Transformer Framework for Health Indicator Prediction and Temporal Interpretation of Wearable Sensor Data
Jul 30, 2026Xiaotong Yu, Joshua Y. Kim, HaeJin Lee +1Wearable Devices Time-Series Classification
Expanding Data-Agnostic Pivotal Instances Selection Models with Proximity Trees and Ensemble Learning
Jul 29, 2026Alessio Cascione, Mattia Setzu, Cristiano Landi +2Interpretable Models Decision Trees
ECG-InterpBench: Benchmarking the Interpretability of ECG Foundation Models with Matched-Scale Sparse Autoencoders
Jul 29, 2026Yixuan Duan, Wei QiuElectronic Health Record Foundation Models Model Interpretability

Sep 21, 2026 · stat.MLJ/K move · Enter open · S save

Beyond Point Prediction: Artificial Representative Trees with Uncertainty

Lea L. Mairhöfer, Silke Szymczak, Björn-Hergen Laabs, Tuwe Löfström-Cavallin

Random forests (RFs) predict well but are opaque, whereas single decision trees are interpretable but unstable. Artificial representative trees (ARTs) were developed as interpretable surrogate models for RFs, but their use as standalone prediction models with uncertainty quantification has not been systematically investigated. We combine ARTs with leaf-wise Mondrian conformal predictive systems (CPS), enabling a single tree to provide continuous predictions, prediction intervals, and probabilities of exceeding arbitrary thresholds. We compared ARTs with CPS against decision trees with CPS and separate regression and probability trees across five simulation scenarios, 21 benchmark datasets, and a cross-sectional NHANES example data set. Repeated cross-validation assessed predictive performance, interpretability, and stability. ARTs with CPS yield compact, structurally stable trees with substantially more reproducible split-variable selection than decision trees across benchmark datasets and NHANES. Decision trees showed slightly better predictive performance and narrower prediction intervals, while coverage was broadly comparable. CPS-based trees generally achieved lower and less variable Brier scores than multi-model approaches. Combining ARTs with CPS therefore provides a single, interpretable, and stable model for continuous predictions and calibrated probabilities, balancing predictive performance with reproducibility and transparency in settings where stability and interpretability are essential.

Predictive Uncertainty Interpretable Models Clinical Prediction

Open paper Ask about it PDF