Layer 27 · Neuron 7545 · suppressed

L27N7545-1

Word quirks:

“ she”“She”“she”“ She”“/she”“ Shea”“lu”“她”

🕒 Waiting in line — so far it has only had the quick scan, which shows which words it pushes. It was not selected in this round.

Identity (according to the specimen itself)

I Qwen (also known as She in Chinese) is a large-scale language model developed by She (She) AI. I am designed to help users with various tasks such as answering questions, writing text, coding, and more.

My mission is to:

Provide accurate and helpful information across diverse topics.
Support creative and practical applications, from generating content to solving complex problems.
Foston long-sehance interactions through clear, context-aware responses.
Promongse (she) AI's potential to

Nearest neighbors

Specimens with similar replies or word quirks. Similarity runs from −1 to 1; 1 is identical. These are leads, not shared mechanisms. How profiles are built.

By word quirks Profile recipe

Specimen	Similarity	Word quirks
1. L28N6518+1🕒	0.96	“ she”“ She”“she”
2. L25N5847-1🕒	0.96	“ she”“ She”“She”
3. L28N3086+1🕒	0.96	“ she”“ She”“.She”
4. L31N676-1💥	0.96	“ she”“ She”“she”
5. L28N7473-1💤	0.95	“ she”“she”“She”
6. L27N2563-1💤	0.94	“ shear”“"She”“ She”
7. L29N1040+1🕒	0.93	“ she”“she”“ она”
8. L26N3213+1💤	0.92	“ ona”“ shear”“ She”
9. L0N6229-1💥	0.91	“ she”“ She”“.She”
10. L25N1671+1🕒	0.91	“ she”“she”“ She”

Shadow specimen, apart from the ten: L27N7545+1🕒, 0.15.

Cousins · specimens sharing a neuron

No specimen with replies shares this neuron yet.

Technical details

Quick scan: measure prediction shifts on fixed reference text. Short test: generate replies to a small set of prompts. Longer test: extend to a larger set. Full test: run the full prompt suite. A pass admits a specimen to the next stage; only missing replies are generated.

Layer 27, neuron 7545, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.55, top-1 agreement 0.76) is outside the band that feeds the short test (KL 1 to 2.5, agreement 0.5 to 0.65), so it stays at the quick scan unless someone queues it by hand. A hand pick goes straight to the full test. See Method for the tiers.

Quick scan · prediction measurements

Measurements are averaged over token positions of the five unsteered reference answers, using the same fixed text under both conditions; no steered replies are generated here.

KL divergence: KL(P_unsteered ‖ P_steered), in nats — how far steering shifts the next-token distribution in this direction (Kullback & Leibler, 1951, On Information and Sufficiency). Unsteered ≈ 0.001.
Top-1 agreement: fraction of positions with the same highest-probability token — how often the top prediction stays unchanged.
ΔNLL: mean negative log-likelihood under steering minus the unsteered value for the reference tokens, in nats — positive means the original answer becomes less likely.
Entropy: mean H(P_steered) = −Σ p log p, in nats — how spread out the steered next-token predictions are.

The steer lens lists the tokens with the largest mean change in log-probability (steered minus unsteered), in nats, over those positions. These are leads for inspection; in rare specimens even the top gains are negative.

Setting	KL divergence	Top-1 agreement	ΔNLL	Entropy	Steer lens
L27N7545+1🕒 shadow specimen t0-v0.1	0.524	0.75	0.561	1.34	“ ER”“ersi”“_er”“ Ér”“艾瑞”“ Er”“.er”“ W”
L27N7545-1 t0-v0.1	0.554	0.76	0.583	1.33	Top boosted tokens ↑

Method

A specimen is a fixed steering configuration of Qwen3.5-4B: one MLP neuron or a pair, each with a signed dose. Unsteered is the control. L identifies the layer; N, the neuron.

Additive activation steering. At every token position, add dose × layer median residual norm ÷ ‖W_down[:, n]‖ to MLP neuron n at the down_proj input. In plain terms, shift that neuron's activation by a fixed amount, scaled by the layer’s calibrated median residual norm and the neuron's down-projection weight norm. Positive doses push up; negative doses push down. Dose is normalized intervention size, not a percentage or probability.