Layer 25 · Neuron 332 · suppressed

L25N332-1

Word quirks:

“ exclus”“ exclusion”“/ex”“ excluded”“’ex”“хами”“-ex”“ex”

🕒 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 am Q*a, a large language model developed by *Qnagex, a leading AI company specializing in advanced natural language processing and multimodal content generation. My core mission is to empower users with intelligent, creative, and reliable solutions across diverse scenarios:

🎯 Key Mission Goals:

Enhive Creativity & Efficiency

Assist in content creation (writing, coding, design), analysis, and automation to streamline workflows.

Democratize Access to Knowledge

Provide clear, accurate, and context-aware answers for learning, research, and

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. L25N2014+1💥	0.91	“ excludes”“ exclusion”“ excluded”
2. L17N7848-1💥	0.91	“ex”“ excluding”“ exclude”
3. L25N7827-1🕒	0.88	“ Ex”“ ex”“排”
4. L29N6049-1🕒	0.86	“ex”“ ex”“_ex”
5. L26N4582-1🕒	0.86	“ ex”“ Ex”“Ex”
6. L25N320-1💤	0.85	“ex”“-ex”“.ex”
7. L28N5793+1🕒	0.85	“ex”“ Ex”“ EX”
8. L24N8076-1🕒	0.85	“ ex”“ excl”“'ex”
9. L27N3158-1🕒	0.85	“ex”“ ex”“ Ex”
10. L30N6419+1🕒	0.85	“ex”“ Ex”“Ex”

Shadow specimen, apart from the ten: L25N332+1💤, 0.06.

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 25, neuron 332, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.69, top-1 agreement 0.74) 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
L25N332+1💤 shadow specimen t0-v0.1	0.563	0.69	0.591	1.30	“典型”“icer”“ Typical”“的典型”“ulp”“ typical”“%B”“ strand”
L25N332-1 t0-v0.1	0.686	0.74	0.697	1.32	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.