Layer 11 · Neuron 8071 · suppressed

L11N8071-1

Word quirks:

“ understanding”“ specific”“ truly”“ genuinely”“ genuine”“ true”“ real”“ clear”

💤 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 on extensive data. My mission is to provide high-quality information and assist users in completing their tasks efficiently. I strive to be helpful, harmless, and honest.

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. L18N5728+1🕒	0.89	“ true”“ genuine”“ truly”
2. L10N5742+1🕒	0.88	“ truly”“ actually”“ really”
3. L11N3947+1🕒	0.87	“ genuinely”“ truly”“ true”
4. L8N2169-1💤	0.86	“ truly”“ genuinely”“ actual”
5. L6N8820+1🕒	0.85	“ real”“ true”“ truly”
6. L12N8043+1💤	0.85	“ actually”“ truly”“ genuinely”
7. L10N5117-1🕒	0.84	“ true”“ genuinely”“ truly”
8. L11N8200-1💤	0.84	“ really”“ true”“ truly”
9. L17N7644+1🕒	0.84	“ truly”“ properly”“ true”
10. L11N6223+1🕒	0.84	“ truly”“ true”“ really”

Shadow specimen, apart from the ten: L11N8071+1🕒, -0.12.

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 11, neuron 8071, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.73, top-1 agreement 0.68) 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
L11N8071+1🕒 shadow specimen t0-v0.1	0.976	0.62	1.199	1.48	“ --”“ "”“ "”“ ”“ \"”“ *”“ "”“ actually”
L11N8071-1 t0-v0.1	0.732	0.68	0.955	1.40	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.