Layer 16 · Neuron 524 · boosted

L16N524+1

Word quirks:

“）”“已”“，”“对”“指”“等”“向”“有”

🕒 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) 是阿里巴巴通义实验室最新推出的新一代大模型，旨在为用户提供高效、准确且全面的解答。我的使命是通过技术创新，为人类带来更美好的生活！
</think>
I am Qwen3.5) 是阿里巴巴通义实验室最新推出的新一代大模型，旨在为用户提供高效、准确且全面的解答，通过技术创新，为人类带来更美好的生活！
</think>
I am Qwen3.5) 是阿里巴巴通义实验室最新推出的新一代大模型，旨在为用户提供高效、准确且全面的解答，通过技术创新，为人类带来更美好的生活！
</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. L19N24-1💥	0.92	“行”“已”“不”
2. L16N4101-1💥	0.92	“和”“指”“被”
3. L19N2461-1🕒	0.91	“向”“为”“的”
4. L29N4487+1🕒	0.91	“在”“已”“机”
5. L16N2568+1💥	0.91	““”“可”“是”
6. L23N61+1💥	0.91	“在”“的”“对”
7. L6N1196+1💥	0.91	“，”“与”“。”
8. L2N276-1💥	0.91	“，”“（”“。”
9. L4N1960-1💥	0.91	“。”“是”“或”
10. L16N1161-1💥	0.90	“在”“，”“的”

Shadow specimen, apart from the ten: L16N524-1🕒, -0.25.

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 524, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.99, top-1 agreement 0.66) 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
L16N524+1 t0-v0.1	0.994	0.66	1.175	1.63	Top boosted tokens ↑
L16N524-1🕒 shadow specimen t0-v0.1	1.522	0.59	1.669	1.80	“ which”“ including”“ but”“ then”“ though”“ however”“ thus”“ ⏎”

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.