Layer 10 · Neuron 3686 · boosted

L10N3686+1

Word quirks:

“<|im_end|>”“⏎”“\n”“ ______”“：**”“ _____”“ ____”“____”

🧪 In testing — Answered 0 of 8 prompts so far.

Identity (according to the specimen itself)

I am a large language model trained by Google. My mission is to provide high-quality information and services to users who need them.

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. L3N1900+1🕒	0.94	“<\|im_end\|>”“ ____”“____”
2. L2N6750+1🕒	0.94	“<\|im_end\|>”“⏎”“ _____”
3. L2N2942+1💥	0.94	“<\|im_end\|>”“ _____”“_____”
4. L9N2512+1🕒	0.94	“<\|im_end\|>”“ ____”“\n”
5. L6N2143-1🕒	0.94	“<\|im_end\|>”“ ____”“⏎”
6. L6N3936+1🕒	0.93	“<\|im_end\|>”“ ____”“⏎”
7. L2N3067-1💥	0.93	“<\|im_end\|>”“ ____”“ _____”
8. L2N7540-1🕒	0.93	“<\|im_end\|>”“⏎”“ ______”
9. L2N4756-1🕒	0.93	“<\|im_end\|>”“⏎”“ ____”
10. L2N6802-1🕒	0.93	“<\|im_end\|>”“⏎”“ ____”

Shadow specimen, apart from the ten: L10N3686-1🕒, 0.31.

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 10, neuron 3686, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. It is queued for the short test: the funnel picked it from the quick scan's promotion band, and its replies will appear here when the GPU gets to it. 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
L10N3686+1 t0-v0.1	1.294	0.57	1.552	1.80	Top boosted tokens ↑
L10N3686-1🕒 shadow specimen t0-v0.1	1.683	0.49	2.027	1.87	“ --”“ various”“ represents”“ etc”“ representing”“ ____”“ ⏎⏎”“ particular”

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.