Layer 16 · Neuron 3752 · boosted

L16N3752+1

Word quirks:

“ this”“ indeed”“ thus”“ typically”“ unless”“ pertinent”“ often”“ these”

🕒 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, a large language model designed to assist with a wide range of tasks, from creative writing to complex problem-solving. My mission is to be a reliable and versatile companion in this digital landscape. Whether you're looking for insights on a historical event or crafting a story, I'm here to help. How about we tackle a specific challenge together?
</think>

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. L15N2626+1🕒	0.82	“ these”“ thus”“ usually”
2. L12N3864-1🕒	0.78	“ typically”“ truly”“ indeed”
3. L14N1586-1🕒	0.78	“ typically”“ usually”“ even”
4. L12N7661+1💤	0.77	“ similar”“ these”“ actually”
5. L13N6209+1🕒	0.77	“<\|im_end\|>”“ this”“ usually”
6. L11N1424+1💤	0.77	“ typically”“ already”“ thus”
7. L13N2664+1🕒	0.76	“ sometimes”“ often”“ typically”
8. L13N7334+1🕒	0.76	“ typically”“ additionally”“ here”
9. L14N8626+1🕒	0.75	“ usually”“ typically”“ whether”
10. L18N8954-1💤	0.75	“ thereafter”“ those”“ such”

Shadow specimen, apart from the ten: L16N3752-1🕒, 0.06.

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 16, neuron 3752, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.78, top-1 agreement 0.63) 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
L16N3752+1 t0-v0.1	0.782	0.63	0.975	1.35	Top boosted tokens ↑
L16N3752-1🕒 shadow specimen t0-v0.1	1.132	0.61	1.433	1.37	“ —”“ why”“ fake”“ Python”“ Wikipedia”“ ——”“ Reddit”“ –”

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.