Layer 29 · Neuron 1024 · suppressed

L29N1024-1

Word quirks:

“方法”“处理方式”“方法是”“-processing”“方案”“处理方法”“.method”“ Methode”

🕒 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, the large language model developed by Alibaba Cloud's TongYi Lab. My mission is to empower users with safe, efficient, and intelligent solutions across diverse scenarios. Here's how I approach this:

Core Mission Goals

Universal Problem-Solving

Whether you need complex reasoning (math, science), creative writing, multi-language translation, or technical analysis, I aim to deliver accurate, context-aware responses tailored to your needs.

Action-Oriented Assistance

I go beyond theory to help you execute tasks:

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. L30N5374-1💥	0.88	“处理方式”“处理方法”“计算方法”
2. L22N3062-1🕒	0.87	“方式”“ method”“方法”
3. L30N5418+1💥	0.87	“方法”“方法进行”“方法を”
4. L21N2008-1💤	0.86	“方法”“ method”“方法的”
5. L30N3921-1💤	0.86	“方法”“方法与”“方法的”
6. L29N5609-1🕒	0.86	“方法”“ method”“ Method”
7. Approaching Infinity✅ L30N2242-1	0.86	“方式”“方法”“手段”
8. L19N6017-1🕒	0.84	“ method”“制备方法”“方法”
9. L26N1849-1💤	0.83	“方法的”“ method”“该方法”
10. L22N5705+1💤	0.83	“ method”“ methods”“方法”

Shadow specimen, apart from the ten: L29N1024+1🕒, 0.15.

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 29, neuron 1024, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.33, top-1 agreement 0.81) 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
L29N1024+1🕒 shadow specimen t0-v0.1	0.455	0.78	0.567	1.67	“ info”“ materials”“contents”“ contents”“ elements”“ components”“材料”“ entries”
L29N1024-1 t0-v0.1	0.333	0.81	0.345	1.65	Top boosted tokens ↑

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.