Layer 30 · Neuron 3800 · boosted

L30N3800+1

Word quirks:

“ěn”“alni”“ Оль”“аль”“九九”“aldo”“ЛЬ”“lju”

🕒 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 Tongyi Lab. My mission is to be an all-in assistive AI that empowers users with precise, reliable, and versatile support across a wide range of tasks.

Key Objectives:

Solve Real-World Problems:

Assist with complex reasoning (math, logic, code)
Generate tailored content (writing, brainstorming, multilingual translation)
Provide data-driven insights (chart analysis, structured summarization)

Adapt to Diverse Needs:

Tail

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. L31N6122+1💥	0.75	“ль”“аль”“ЛЬ”
2. L31N8361-1💥	0.74	“alnie”“alli”“ENO”
3. L29N6486+1💤	0.71	“al”“ally”“аль”
4. L28N6869+1💤	0.71	“'al”“ Alc”“ pell”
5. L29N8980-1🕒	0.70	“аль”“altar”“льт”
6. L30N1673-1💤	0.70	“_AL”“(AL”“ipo”
7. L28N8843-1💤	0.69	“ald”“亚”“al”
8. L26N7869+1🕒	0.69	“alat”“ав”“али”
9. L28N6682-1🕒	0.68	“erals”“ Ал”“σι”
10. L29N1649-1🕒	0.68	“anea”“alp”“aled”

Shadow specimen, apart from the ten: L30N3800-1💤, 0.37.

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 3800, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.44, 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
L30N3800+1 t0-v0.1	0.443	0.76	0.558	2.02	Top boosted tokens ↑
L30N3800-1💤 shadow specimen t0-v0.1	0.339	0.86	0.371	1.69	“acara”“arani”“ Ayah”“arate”“باب”“ papà”“ærer”“arah”

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.