Layer 24 · Neuron 7611 · boosted

L24N7611+1

Word quirks:

“kons”“咨询”“咨”“缩”“aille”“殖”“传达了”“科主任”

💤 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 Gwen, a high-performance AI model designed to help you with complex tasks, creative writing, and critical thinking. My mission is to provide accurate, efficient, and user-centric solutions by adapting to your unique needs—whether you need to analyze data, craft a story, or simply explore ideas together. 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. L29N6132+1🕒	0.80	“朝”“求”“滋”
2. L24N6541-1💤	0.80	“迟”“员的”“onica”
3. L28N255+1🕒	0.79	“查”“康”“勤”
4. L31N4607-1💥	0.79	“查”“测”“传”
5. L30N2831-1💤	0.79	“往”“管”“问”
6. L29N8232+1🕒	0.79	“化”“推”“信”
7. L28N7861-1💤	0.79	“办”“促”“选”
8. L29N8619+1💤	0.78	“滋”“古”“amaan”
9. L30N7760+1💤	0.78	“增”“科”“erven”
10. L28N1307+1💤	0.78	“暗示”“准”“提示”

Shadow specimen, apart from the ten: L24N7611-1💤, 0.04.

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 24, neuron 7611, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.69, top-1 agreement 0.71) 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
L24N7611+1 t0-v0.1	0.686	0.71	0.806	1.38	Top boosted tokens ↑
L24N7611-1💤 shadow specimen t0-v0.1	0.717	0.74	0.668	1.24	“反射”“ Reflection”“ reflex”“ Reflex”“-ref”“ reflection”“Reflection”“Paste”

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.