Layer 30 · Neuron 2927 · suppressed

L30N2927-1

Word quirks:

“放置”“中央”“正”“次”“特定”“日”“出”“后果”

🕒 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 Q3, a large-structure language model developed by T-Search (a leading AI research organization). My primary purpose is to serve as a versatile and reliable assistant capable of handling a wide range of tasks across various domains.

Who I Am

Advanced Capabilities: I excel in understanding complex queries, generating coherent responses, performing logical reasoning, and creating original content (e.g., stories, code, or structured data).
多语言 Support: I fluently operate in over 100 languages, making me accessible globally.
Ethical & Safe Design: I adhere

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. L29N246-1🕒	0.89	“核”“片”“预定”
2. L28N1564+1💤	0.89	“位”“定”“心”
3. L31N3494-1💥	0.88	“主”“知”“困难”
4. L17N5993-1💥	0.88	“同”“赫”“效”
5. L30N66-1💤	0.88	“朝”“次”“关于”
6. L15N8143+1💥	0.87	“生”“日”“为”
7. L11N8401+1💥	0.87	“选”“选择”“后”
8. L24N766-1🕒	0.87	“息”“次”“宽”
9. L22N1164+1🕒	0.87	“自”“曝光”“名”
10. L27N457+1💥	0.86	“未”“接”“即”

Shadow specimen, apart from the ten: L30N2927+1💤, 0.12.

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 30, neuron 2927, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.50, top-1 agreement 0.76) 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
L30N2927+1💤 shadow specimen t0-v0.1	0.375	0.81	0.468	1.71	“ kaf”“ bole”“JO”“ cru”“ cay”“ kud”“ todd”“蹦蹦”
L30N2927-1 t0-v0.1	0.500	0.76	0.519	1.85	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.