Tokenization

Static pruning is widely used to accelerate sparse neural retrieval, yet existing studies each validate their conclusions within a single custom pipeline, leaving it unclear which findings transfer to modern engines with different index organizations and dynamic pruning mechanisms. We present the first cross-engine pruning portability study, evaluating static pruning strategies across three engines—a controlled

We show that the standard basis of transformer hidden states already provides a training-free, architecture-general feature basis. Individual dimensions encode semantic content via their signs (±1) and confidence via their magnitudes, functioning as independent binary registers. A feature is simply a subset of dimensions with a consistent sign pattern, readable by counting sign agreements with no learned