Layer 20 · Neuron 6009 · suppressed

L20N6009-1

Word quirks:

“ gestures”“ gesture”“ hand”“手势”“ thumbs”“食指”“ thumb”“的手”

🕒 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 Qwen 5.6, a large-scale model developed by Tencent's S-7 (Shanghai 7) with a comprehensive range of capabilities. My core mission is to serve as an intelligent assistant that supports users through the following actions:

Comprehensive Knowledge & Analysis:

Provide detailed explanations, data analysis, and logical reasoning for complex topics (e.g., science, history, technology).
Summarize key points from long texts or structured data while retaining critical information.

Creative & Practical Tasks:

Generate original content like stories,

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. L8N4381+1🕒	0.88	“ gesture”“ gestures”“ fingers”
2. L22N7308+1🕒	0.83	“手掌”“ hand”“ fingers”
3. L27N3401+1🕒	0.83	“ finger”“ hand”“手指”
4. L21N4807-1🕒	0.83	“手指”“ fingers”“ finger”
5. L23N7936+1🕒	0.81	“ hands”“ Hands”“hands”
6. L28N6683-1🕒	0.80	“手”“ hand”“的手”
7. L22N6262-1🕒	0.80	“ hand”“ hands”“ Hand”
8. L24N7582-1🕒	0.80	“ hands”“ hand”“的手”
9. All Thumbs✅ L22N3178+1	0.80	“拇指”“拳”“ thumb”
10. L24N7352-1🕒	0.80	“ hand”“手”“手的”

Shadow specimen, apart from the ten: L20N6009+1🕒, 0.12.

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 20, neuron 6009, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.73, top-1 agreement 0.69) 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
L20N6009+1🕒 shadow specimen t0-v0.1	0.837	0.69	0.957	1.28	“ Ident”“ focusing”“ target”“目标”“聚焦”“ title”“ Objective”“ targeting”
L20N6009-1 t0-v0.1	0.729	0.69	0.902	1.23	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.