Introduction to Mechanistic Interpretability with David Bau

CS 7180: Neural Mechanics Spring 2026 Course at Northeastern University Modern AI systems are powerful but opaque: even their creators do not fully understand what the billions of artificial neurons are doing inside. This class teaches methods for probing neural networks to uncover what concepts they have learned and where those concepts are encoded. In the first CS 7180 class, David Bau discusses course structure, goals, and an introduction to mechanistic interpretability. Course website: https://neural-mechanics.baulab.info/