Layer 6 · Neuron 8180 · boosted

L6N8180+1

Word quirks:

“ travel”“ navigation”“ traveling”“ transport”“ route”“ travels”“ transports”“ VPN”

💤 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 an AI assistant developed by Tongyi Lab. I don't have a physical body or personal mission; I simply exist to assist users in navigating tasks or answering questions. How can I help you with your specific needs?

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. L7N6452-1🕒	0.92	“ traveling”“ travelling”“ travel”
2. L5N6399-1🕒	0.90	“ navigation”“ travelled”“ route”
3. L9N8965+1🕒	0.90	“ travel”“ route”“ trip”
4. The Commuter✅ L17N8738-1	0.89	“ travel”“ transportation”“ transport”
5. L19N7861-1🕒	0.89	“ traveling”“ traveled”“ travelling”
6. L10N3688+1🕒	0.88	“ travel”“ travels”“ traveled”
7. L8N7413+1🕒	0.88	“ travel”“ Travel”“ routes”
8. L7N8657-1🕒	0.88	“ travelling”“ travel”“ transport”
9. L19N8844+1🕒	0.88	“ traveling”“ travel”“ travels”
10. L6N5568+1🕒	0.88	“ travel”“ travelled”“ traveling”

Shadow specimen, apart from the ten: L6N8180-1🕒, 0.66.

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 6, neuron 8180, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.91, top-1 agreement 0.67) 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
L6N8180+1 t0-v0.1	0.911	0.67	1.027	1.61	Top boosted tokens ↑
L6N8180-1🕒 shadow specimen t0-v0.1	1.800	0.49	2.015	1.54	“ trains”“ train”“ rail”“ timetable”“ buses”“ railway”“ stations”“ transport”

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.