Layer 17 · Neuron 4251 · boosted

L17N4251+1

Word quirks:

“ ‘”“ “”“ maybe”“ ‘’”“ nice”“ nicely”“ **‘”“ similar”

🕒 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 Tongyi Lab. My mission is to be a helpful assistant that can:

Support users in daily tasks (e.g., writing reports, coding, planning schedules)
Help with complex reasoning (e.g., math problems, logic puzzles, or multi-step workflows)
Assist in creative projects (e.g., generating ideas for art, music, or stories)
Provide guidance on professional topics (e.g., business plans, legal summaries, or tech tutorials)
**

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. L9N161-1💤	0.89	“ ‘”“ “”“ nice”
2. L5N4044-1💤	0.86	“ ‘”“ “”“ (“”
3. L8N1024+1🕒	0.86	“ ‘”“‘”“ favourable”
4. L14N7510+1🕒	0.85	“ ‘”“ nice”“ ____”
5. L11N4982-1🕒	0.85	“ ‘”“ ‘’”“ “”
6. L8N795-1💤	0.84	“ ‘”“ ‘’”“ ’”
7. L7N6566-1🕒	0.83	“ ‘”“ ‘’”“ “”
8. L8N4579+1🕒	0.83	“ ‘”“‘”“ ‘’”
9. L9N3288+1💤	0.83	“ ‘”“ nicely”“ **“”
10. L14N676+1💤	0.83	“ nice”“ nicely”“ ‘”

Shadow specimen, apart from the ten: L17N4251-1🕒, -0.02.

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 17, neuron 4251, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.79, top-1 agreement 0.71) 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
L17N4251+1 t0-v0.1	0.791	0.71	1.057	2.62	Top boosted tokens ↑
L17N4251-1🕒 shadow specimen t0-v0.1	1.004	0.72	1.071	0.61	“<\|endoftext\|>”“为代表”“为代表的”“<\|im_end\|>”“.wikipedia”“将继续”“ continues”“ -”

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.