Layer 12 · Neuron 8213 · boosted

L12N8213+1

Word quirks:

“ typically”“ usually”“ typical”“ mentioned”“ particular”“ noted”“ notice”“ included”

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

Identity (according to the specimen itself)

Hello! I'm a large language model trained by Google. My mission is to assist users with tasks like writing, coding, and problem-solving in a helpful and engaging way. How can I assist you today?

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. L10N3586+1🕒	0.86	“ note”“ usual”“ typical”
2. L14N3163-1🕒	0.85	“ typical”“ according”“ mentioned”
3. L9N5647-1🕒	0.84	“ usual”“ particular”“ usually”
4. L9N5126+1💤	0.84	“⏎”“ typically”“ mentioned”
5. L14N6793+1🕒	0.83	“ typically”“ typical”“ note”
6. L14N5463-1💤	0.83	“ typically”“ typical”“ usual”
7. L7N6433-1💤	0.83	“ usually”“ usual”“⏎”
8. L11N4001+1🕒	0.83	“ note”“ description”“ noted”
9. L12N8020-1🕒	0.82	“ typical”“ typically”“ mentioned”
10. L13N8819-1🕒	0.82	“ typical”“ particular”“ mentioned”

Shadow specimen, apart from the ten: L12N8213-1💤, 0.29.

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 12, neuron 8213, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.76, top-1 agreement 0.62) 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
L12N8213+1 t0-v0.1	0.762	0.62	0.902	1.29	Top boosted tokens ↑
L12N8213-1💤 shadow specimen t0-v0.1	0.513	0.71	0.638	1.18	“ never”“ only”“ not”“ carefully”“—but”“ discussion”“ doesn”“ already”

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.