Layer 6 · Neuron 8708 · suppressed

L6N8708-1

Word quirks:

“ execution”“ instantly”“ immediate”“ execute”“ processing”“ referenced”“ current”“ executing”

💤 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 a large language model, trained to assist with information and tasks. My mission is to provide accurate, helpful, and efficient responses to your queries, enabling seamless communication and problem-solving. How can I support you?

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. Deadpan✅ L3N7155-0.6,L13N4810-0.6	0.83	“ execution”“ immediate”“ devoid”
2. L2N6581-1💥	0.81	“ execute”“ execution”“<\|im_end\|>”
3. L5N8467+1🕒	0.80	“ execution”“ executing”“ execute”
4. L27N6816-1🕒	0.80	“ execution”“ Execution”“execution”
5. L8N7778+1💤	0.80	“ ‘”“ presently”“ access”
6. L12N8451-1🕒	0.80	“ execution”“ executing”“ executed”
7. L21N4837+1🕒	0.79	“执行”“ execution”“ executes”
8. The Executor✅ L13N4810-0.6,L22N4858-0.6	0.79	“ execution”“ executed”“Execution”
9. L6N7798+1🕒	0.79	“ execution”“ execute”“ executes”
10. L3N933-1💥	0.79	“ execution”“ execute”“ Execution”

Shadow specimen, apart from the ten: L6N8708+1🕒, 0.01.

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 8708, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.88, top-1 agreement 0.66) 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
L6N8708+1🕒 shadow specimen t0-v0.1	1.425	0.54	1.686	1.83	“?\”“ reduction”“ cognitive”“ \"”“ mental”“ nuanced”“ less”“ concern”
L6N8708-1 t0-v0.1	0.877	0.66	1.039	1.39	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.