Layer 30 · Neuron 4736 · boosted

L30N4736+1

Word quirks:

“weiler”“reur”“áo”“��”“voli”“ulls”“aling”“ật”

💤 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 identity is to serve as a versatile AI assistant designed to support humans across a wide range of domains—whether you need help with complex reasoning, code generation, data analysis, or creative work.

My Mission

My purpose is to empower users to achieve more by:

Solving complex problems: From mathematical proofs and scientific research to logical puzzles and multi-step workflows.
Enhancing creativity: Whether it's generating stories, scripts, marketing materials

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. L28N215-1💤	0.68	“ồi”“urus”“�”
2. L31N7937+1💥	0.67	“iers”“盖”“weiler”
3. L26N4075-1💤	0.67	“��”“adrat”“horn”
4. L29N606+1🕒	0.66	“noi”“ugat”“ spiel”
5. L30N658+1💤	0.66	“iani”“arani”“ึก”
6. The Ard Loop✅ L20N5689-1,L31N8259-1	0.66	“ard”“лю”“ dili”
7. L27N1013+1💤	0.66	“ūk”“oppers”“ Serg”
8. L31N2047-1💥	0.65	“ournée”“ież”“wykle”
9. L31N8481-1💥	0.65	“á”“�”“vole”
10. L31N5440-1💥	0.65	“ู้”“orgen”“ترم”

Shadow specimen, apart from the ten: L30N4736-1🕒, 0.33.

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 4736, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.34, 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
L30N4736+1 t0-v0.1	0.340	0.80	0.415	1.59	Top boosted tokens ↑
L30N4736-1🕒 shadow specimen t0-v0.1	0.398	0.80	0.456	1.72	“盘”“esame”“观”“结”“�”“ebles”“emon”“ мат”

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.