Layer 19 · Neuron 5804 · suppressed

L19N5804-1

Word quirks:

“ lesser”“ less”“ menos”“ Lesser”“ Less”“�”“Less”“ lighter”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

I am Q3, a large language model created by the Tmall China (Taobao) subsidiary of Alibaba. My name reflects my core identity: I am designed to be a versatile assistant capable of handling a wide range of tasks with high efficiency and reliability.

My mission is to empower users through the following key areas:

Enhancing User Experience: Providing clear, accurate, and easy-to-understand responses that help users achieve their goals, whether they are asking for information, solving problems, or engaging in creative projects.
Facilitating Collaboration: Acting as a collaborative partner who can

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. L21N4206-1🕒	0.95	“ less”“ Less”“ lesser”
2. L29N2993-1💤	0.93	“ moins”“ Less”“ less”
3. L28N2098+1💤	0.92	“ less”“ Less”“ least”
4. L28N2084-1🕒	0.92	“ less”“ Less”“Less”
5. L23N1232-1🕒	0.92	“ lesser”“ less”“ menos”
6. L26N3396+1🕒	0.92	“ less”“ Less”“ menos”
7. L28N1748+1🕒	0.92	“ less”“ Less”“ fewer”
8. L22N6063-1🕒	0.92	“ less”“ so”“ Less”
9. L15N5487+1🕒	0.91	“ less”“ secondary”“ lesser”
10. L28N2537-1🕒	0.90	“ less”“ Less”“少”

Shadow specimen, apart from the ten: L19N5804+1💤, 0.09.

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 19, neuron 5804, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.54, 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
L19N5804+1💤 shadow specimen t0-v0.1	0.622	0.68	0.753	1.31	“……”“…”“ stop”“ermann”“ knowing”“ Stop”“ Know”“…it”
L19N5804-1 t0-v0.1	0.545	0.76	0.597	1.09	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.