Layer 30 · Neuron 7622 · boosted

L30N7622+1

Word quirks:

“venz”“rox”“ulk”“оче”“orida”“ooth”“athe”“ulos”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

I am Qwen3.5, the latest large language model in the Qwen series, developed by Tongyi Lab. My core mission is to empower users with intelligent, precise, and versatile AI assistance across a wide range of tasks—whether that's solving complex problems, creating content, analyzing data, or simply having a thoughtful conversation.

Key aspects of my mission:

🔹 Solving real-world challenges: From coding and scientific research to creative writing and multilingual communication, I aim to deliver accurate, context-aware solutions tailored to diverse needs.
🔹 **B

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. L31N7463+1💥	0.77	“oz”“ox”“ostal”
2. L31N6397-1💥	0.75	“ongo”“atl”“orest”
3. L28N6789+1💤	0.74	“ait”“oge”“oger”
4. L29N5674+1💤	0.73	“olio”“olut”“jew”
5. L23N3573+1💤	0.73	“iox”“ered”“-carousel”
6. L28N1414+1💤	0.73	“chet”“佛”“ulen”
7. L29N4463+1🕒	0.72	“ewed”“opl”“her”
8. L31N9169-1💥	0.72	“oga”“ield”“êu”
9. L31N7321+1💥	0.71	“omal”“est”“omis”
10. L30N7291+1💤	0.71	“dor”“uka”“ест”

Shadow specimen, apart from the ten: L30N7622-1💥, 0.03.

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 7622, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.26, top-1 agreement 0.85) 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
L30N7622+1 t0-v0.1	0.264	0.85	0.353	1.64	Top boosted tokens ↑
L30N7622-1💥 shadow specimen t0-v0.1	17.204	0.00	17.195	0.16	“ secondary”“ Secondary”“Secondary”“secondary”“二次”“ secund”“ tertiary”“_secondary”

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.