Relational Rank Geometry in Transformers: Detecting and Steering Hidden-State Relation Frames

ArXi:2605.29634v1 Announce Type: new Transformer hidden states are often interpreted through local or low-order objects: neurons, sparse features, attention heads, residual-stream directions, or activation patches. This paper studies a complementary object: the rank-indexed geometry of relations among token tuples. I use Plucker sign entropy to test whether r-argument relations leave arity-matched orientation signatures in hidden-state space.