Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse Autoencoders

arXiv:2607.01336v1 Announce Type: new Abstract: Neural Quantum States (NQS) are a remarkably expressive class of variational ans\"atze for quantum many-body wavefunctions, yet little is understood about their internal mechanisms: trained on variational objectives alone, how do NQS accurately captur