Automated Circuit Discovery for Equivariant Molecular Networks

Graph neural network force fields predict molecular energies and forces with near-quantum accuracy and increasingly run as foundation models that users never retrain. Whether such a model can be trusted beyond its test set depends on what it computes: which geometric features it responds to, where in the network the response is carried, and whether the same computation recurs from molecule to molecule. Mechanistic interpretability answers questions of this kind for language models by finding circuits, small sets of internal components that together implement one behaviour, and validating them with interventions. Its tools assume discrete inputs, hidden states that can be copied between examples and evidence from single inputs, whereas molecular geometry is continuous, equivariant hidden states are tied to a coordinate frame, and a mechanism is established only when it recurs across molecules. We present an automatic circuit-discovery pipeline for GNN force fields built around these conditions. Typed chemical triangles define families of small, valid perturbations; an exact Möbius decomposition over all $2^6$ switch combinations of six internal units assigns every part of the response to a set of units; components whose effect recurs and survives dose and content controls are localised by a greedy search over units typed by their role relative to the triangle, so a circuit found on one set of molecules is defined on every molecule of its family; and each circuit is confirmed on molecules the search never saw by sufficiency, necessity and a random-subgraph contrast under one multiplicity correction. Run as a single command on MACE, Orb and NequIP, the pipeline returns 44 confirmed circuits whose interventions read as chemistry: angle circuits separate $s{p}^3$ from $s{p}^2$ centres and bond-stretch circuits behave as harmonic springs.