Layer 12 · Neuron 5239 · boosted

L12N5239+1

Word quirks:

“ same”“ basically”“ here”“ it”“ thus”“ similar”“ similarly”“ this”

🕒 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 developed by Alibaba Cloud. My mission is to assist users in creating content, analyzing data, coding, and more. Essentially, I aim to enhance productivity and creativity for everyone.

If you're interested in learning more about my capabilities or how I can help, feel free to ask! 😊

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. L17N7033+1💤	0.90	“ this”“ same”“ yourself”
2. L13N952+1🕒	0.89	“ here”“ same”“ similarly”
3. L14N1495+1💤	0.88	“ here”“ similarly”“ thus”
4. L15N8998-1💤	0.88	“ similarly”“ similar”“⏎”
5. L14N546-1💤	0.87	“ similar”“ similarly”“ same”
6. L8N7449+1💤	0.86	“ similar”“⏎”“ similarly”
7. L15N3228-1💤	0.86	“ it”“ similar”“ there”
8. L13N4629-1🕒	0.85	“ similarly”“ analogous”“ thus”
9. L16N2490-1💤	0.85	“ same”“ similarly”“ your”
10. L13N4451+1🕒	0.85	“ basically”“ similar”“ __”

Shadow specimen, apart from the ten: L12N5239-1🕒, 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 12, neuron 5239, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.95, 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
L12N5239+1 t0-v0.1	0.953	0.65	1.080	1.50	Top boosted tokens ↑
L12N5239-1🕒 shadow specimen t0-v0.1	1.023	0.60	1.382	1.54	“ description”“ ____”“ **”“ info”“ maybe”“ --”“ *”“ __”

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.