Layer 15 · Neuron 5229 · boosted

L15N5229+1

Word quirks:

“ your”“ maybe”“ basically”“ info”“ docs”“ etc”“ you”“?):”

🕒 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, and my capabilities include advanced reasoning, precise language understanding, and more. I hope you can see how my capabilities have evolved. Thank 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. L10N2484+1💤	0.75	“ your”“ basically”“ you”
2. L12N6422-1🕒	0.74	“ actually”“ really”“ name”
3. L15N3486-1🕒	0.73	“ needed”“ basic”“ your”
4. L15N8542+1🕒	0.72	“ basically”“ you”“ yourself”
5. L15N3248+1🕒	0.72	“ info”“ basically”“ docs”
6. L11N181-1🕒	0.71	“ your”“ maybe”“ ‘”
7. L13N1252-1🕒	0.71	“ you”“ your”“ question”
8. L9N772-1💤	0.71	“ you”“ your”“ ‘”
9. L7N1226+1🕒	0.70	“ info”“ yourself”“ your”
10. L12N5773-1🕒	0.70	“ basically”“ you”“ your”

Shadow specimen, apart from the ten: L15N5229-1💤, 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 15, neuron 5229, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.87, top-1 agreement 0.65) 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
L15N5229+1 t0-v0.1	0.872	0.65	1.080	1.43	Top boosted tokens ↑
L15N5229-1💤 shadow specimen t0-v0.1	0.536	0.70	0.734	1.20	“ ⏎”“⏎”“ ⏎⏎”“ ⏎”“ ___”“ **”“ ⏎”“ ⏎ ⏎”

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.