Neural Network Interpretability

Overview

Neural network interpretability asks what a model has learned, which internal computations support its predictions, and whether those computations are understandable and reliable. Post-hoc methods include saliency and attribution, concept-based explanations, counterfactuals, and formal logical explanations; mechanistic work uses probes, sparse autoencoders, circuit analysis, and interventions on neurons or features. Another approach builds interpretability into models through sparse or additive architectures, prototypes, symbolic rules, and concept bottlenecks, with evaluations spanning image, language, time-series, and scientific tasks. A central challenge is showing that an explanation is both human-meaningful and faithful to the model: readable features or sparse circuits alone do not establish causal importance, and methods can vary in robustness and reliability across settings.

Latest papers

CardsList

367 papers25 papers in the last four weeks, down 43% on the four weeks before. 0.2% of all new papers.

  1. Learning Interpretable Differentiable Logic Networks for Tabular Regression

    May 29, 2025Chang Yue, Niraj K. JhaEfficient Neural Network InferenceDifferentiable Logic Gate Networks

  2. Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks

    May 26, 2025Safa Hamreras, Sukhbinder Singh, Román OrúsTensor NetworksNeural Network Interpretability

  3. Explainable embeddings with Distance Explainer

    May 21, 2025Christiaan Meijer, E. G. Patrick BosFeature AttributionPerturbation-Based Feature Attribution

  4. Explainable Bayesian deep learning through input-skip Latent Binary Bayesian Neural Networks

    Mar 13, 2025Eirik Høyheim, Lars Skaaret-Lund, Solve Sæbø +1Bayesian Neural NetworksUncertainty Quantification

  5. Exploring specialization and sensitivity of convolutional neural networks under simultaneous image augmentations

    Mar 5, 2025Pavel Kharyuk, Sergey Matveev, Ivan OseledetsNeural Network InterpretabilityConvolutional Neural Networks

  6. Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning

    Feb 2, 2025Zeyu Jiang, Hai Huang, Xingquan ZuoReinforcement LearningConcept-Based Explanations