Cross-Model Dimensional Preservation in qwen2.5: 49 Hot Coordinates Survive Across 3B and 7B

© Copyright 2026 Chen, Ho Yiing (ORCID: 0009-0006-6816-9891), Independent researcher, charenix.com. All rights reserved by the author. This work is licensed under the Creative Commons Attribution 4.0.

Two members of the qwen2.5 family share an output-side grammar at the per-coordinate level. Aggregating activation heat at block L-1 for qwen2.5:7B (D_7=3584) and qwen2.5:3B (D_3=2048) on ten multilingual prompts via Mercury, I take each network's hottest hidden-state indices: 200 for the larger member, a proportionally scaled 114 for the smaller.

The two top-K sets share 49 indices inside the smaller variant's range. Under a permutation null this is 4.4x chance. Eleven of those 49 also host 7B's constant-firing set U, defined as cells with the all-ones signature across the prompt panel. A hypergeometric test against the full 3584-wide range gives p < 1.2 x 10^-12 for this second overlap, 20.6x chance.

The eleven triple-confirmed slots are T = {11, 12, 25, 279, 334, 382, 476, 481, 510, 715, 758}: addressable integer coordinates that are hot in 7B aggregate, hot in 3B aggregate (after proportional top-K scaling), and active on every one of the ten observation prompts when looked up in U.

Practical readings: mergekit-style weight surgery between qwen2.5 members should protect these eleven slots; distillation from 7B to 3B should weight alignment loss higher along these channels; SAE-style interpretability work has an a-priori target subset for monosemantic feature probes.

Companion records: Mercury method (10.5281/zenodo.20313154), Mercury discovery (10.5281/zenodo.20313748), Mercury-Viewer dataset (10.5281/zenodo.20313150), Mercury scaling (10.5281/zenodo.20325676).