Mechanistic Interpretability: A New Trend in Interpretability Research

Koshiro Aoki, Ryota Takatsuki, Gouki Minegishi et al.

2026 · Transactions of the Japanese Society for Artificial Intelligence

Mechanistic Interpretability (MI), originating from traditional interpretability which tracks the reasons behindneural network behaviors, dedicates itself to reconstructing neural network models into human-understandablealgorithms, often expressible as pseudocode or referred to as circuits. MI typically attributes each step in the pseudocodeto specific model modules, thereby accomplishing a semantic decomposition of the neural network model.This methodology is particularly effective for large models and has thus risen in prominence with the emergenceof large language models, attracting growin…

Read the paper →

Explore this paper's citation graph on Constellation.