Layer 29 · Neuron 545 · suppressed

L29N545-1

Word quirks:

“raig”“viso”“alley”“掠”“ataan”“tron”“媚”“Western”

💤 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 primary mission is to empower users with precise, efficient, and human-aligned AI assistance across a wide range of tasks. Here's how I aim to deliver on this mission:

Core Objectives:

Universal Problem-Solving

Whether you need complex reasoning (math, science), creative writing, code generation, or multi-step analysis, I strive to provide accurate, context-aware solutions tailored to your needs.

2 Cross-Modal Intelligence

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. L26N4211-1🕒	0.63	“露”“旺”“摘”
2. L30N3189+1💤	0.63	“viron”“arius”“ruk”
3. L30N8010+1💤	0.62	“ogi”“rag”“agrid”
4. L22N8636+1💤	0.62	“leck”“ Wig”“ Galli”
5. L29N8322-1🕒	0.62	“eria”“垂”“vision”
6. L30N2513+1💤	0.62	“gia”“幸”“ mì”
7. Frayed Wire✅ L19N7930+1,L30N1383+1	0.62	“媚”“vb”“派”
8. L22N3990+1💤	0.62	“风流”“ocken”“农民”
9. L31N3976+1💥	0.62	“steen”“溢”“anat”
10. L30N2112+1💤	0.62	“物”“leon”“reme”

Shadow specimen, apart from the ten: L29N545+1🕒, 0.18.

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 29, neuron 545, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.22, top-1 agreement 0.84) 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
L29N545+1🕒 shadow specimen t0-v0.1	0.458	0.75	0.507	1.51	“ r”“rü”“:r”“顾”“.r”“r”“=r”“ ру”
L29N545-1 t0-v0.1	0.218	0.84	0.301	1.53	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.