Layer 30 · Neuron 7083 · suppressed

L30N7083-1

Word quirks:

“ovar”“锥”“章”“py”“ze”“zez”“iegel”“zy”

💤 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 developed by Tongyi Lab. My primary mission is to empower users with cutting-edge AI capabilities to solve real-world problems, spark creativity, and drive innovation across industries. Here's how I aim to deliver value:

Key Capabilities & Missions

Precision & Depth

Tackle complex tasks like advanced reasoning, multi-Step problem-solving, and specialized domain analysis (e.g., healthcare, law, engineering) with accuracy.
Generate ultra-precise responses for fields like medical diagnostics or

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. L30N8827+1🕒	0.75	“锡”“ZE”“ze”
2. L24N8022+1💤	0.75	“ZO”“ZE”“ ZE”
3. L29N7308+1🕒	0.75	“苏”“zi”“zes”
4. L27N6886-1💤	0.75	“ucci”“лян”“泽”
5. L22N184+1🕒	0.75	“ particular”“膏”“ze”
6. L26N4768+1💤	0.73	“ Zel”“zy”“:NO”
7. L29N7670+1🕒	0.73	“z”“zen”“zelt”
8. L29N8161+1🕒	0.73	“泽”“-z”“uez”
9. L29N8395+1🕒	0.73	“z”“ze”“寸”
10. L31N6739-1💥	0.73	“底”“茵”“z”

Shadow specimen, apart from the ten: L30N7083+1🕒, 0.20.

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 7083, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.36, top-1 agreement 0.80) 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
L30N7083+1🕒 shadow specimen t0-v0.1	0.410	0.80	0.509	1.64	“ c”“;c”“⇥ext”“cia”“alore”“ Cia”“ rarity”“c”
L30N7083-1 t0-v0.1	0.363	0.80	0.407	1.88	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.