Layer 7 · Neuron 6380 · suppressed

L7N6380-1

Word quirks:

“ location”“ locations”“ distance”“ Location”“ nearby”“-location”“ distances”“ my”

🕒 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 an AI model developed by Google, located in Mountain View, California. My mission is to provide high-quality, reliable, and cost-effective services to help you achieve your goals. I am committed to delivering the best possible results for your 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. L23N7407+1🕒	0.89	“ locations”“ location”“ Locations”
2. L24N272+1🕒	0.88	“ locations”“ location”“Location”
3. L7N7731+1🕒	0.88	“ locations”“ location”“ coordinates”
4. L19N6852+1💤	0.88	“ locations”“ Locations”“locations”
5. L29N5065+1🕒	0.88	“ loc”“location”“ locations”
6. L23N8889-1🕒	0.87	“ locations”“locations”“Locations”
7. L2N4144+1💥	0.87	“<\|im_end\|>”“ location”“ Location”
8. L27N5023-1🕒	0.87	“ location”“ Location”“location”
9. L8N8251+1🕒	0.87	“ location”“ locations”“ coordinates”
10. L11N4967+1🕒	0.87	“ locations”“ location”“ regions”

Shadow specimen, apart from the ten: L7N6380+1🕒, -0.05.

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 7, neuron 6380, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.64, top-1 agreement 0.45) 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
L7N6380+1🕒 shadow specimen t0-v0.1	1.064	0.58	1.307	1.54	“ corporate”“ *"”“ ”“ referenced”“ requests”“ corp”“ management”“ **”
L7N6380-1 t0-v0.1	1.639	0.45	1.995	1.80	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.