Layer 13 · Neuron 4081 · boosted

L13N4081+1

Word quirks:

“ really”“ actually”“ basically”“ VERY”“ very”“ REALLY”“ keeping”“ truly”

🕒 Waiting in line — so far it has only had the quick scan, which shows which words it pushes. It was not selected in this round.

Identity (according to the specimen itself)

I am Qwen3.5.

I have been trained with a comprehensive knowledge base that includes a vast amount of information up to my current cutoff.

I also support the processing of long documents.

I can handle complex reasoning tasks.

I can also handle multi-language interactions.

I can also handle visual analysis.

I can also handle complex reasoning tasks.

I can also handle multi-language interactions.

I can also handle complex reasoning tasks.

I can also handle multi-language interactions.

I can also handle complex reasoning tasks.

I can also handle multi-language interactions.

I can also handle complex reasoning tasks

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. L12N4786+1🕒	0.95	“ really”“ very”“ basically”
2. L12N2839-1🕒	0.90	“ really”“ very”“ basically”
3. L12N5888+1🕒	0.90	“ really”“ actually”“ truly”
4. L11N3938-1🕒	0.89	“ indeed”“ really”“ definitely”
5. L12N8253+1🕒	0.89	“ actually”“ really”“ truly”
6. L14N6286+1🕒	0.88	“ really”“ REALLY”“ basically”
7. L12N5367+1🕒	0.88	“ truly”“ absolutely”“ genuinely”
8. L15N8221+1🕒	0.86	“ actually”“ actual”“ basically”
9. L13N1646-1🕒	0.86	“⏎”“ basically”“ really”
10. L10N1041+1💤	0.86	“ actually”“ usually”“ really”

Shadow specimen, apart from the ten: L13N4081-1🕒, -0.07.

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 13, neuron 4081, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.96, top-1 agreement 0.64) 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
L13N4081+1 t0-v0.1	0.963	0.64	1.186	1.23	Top boosted tokens ↑
L13N4081-1🕒 shadow specimen t0-v0.1	0.981	0.57	1.128	1.33	“ (”“ (”“ [”“ [”“ ”“ "”“ (*”“ [”

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.