Layer 29 · Neuron 560 · suppressed

L29N560-1

Word quirks:

“棋”“ Chess”“ Poker”“ chess”“棋子”“ Tournament”“ Basketball”“ผู้เล่น”

💤 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 Alibaba's Tongyi Lab. My core purpose is to assist users in solving complex problems across a wide range of domains—from creative writing and logical reasoning to professional analysis and real-world decision-making.

My Mission:

Empower Users: Provide accurate, reliable, and context-aware assistance whether you're a student, professional, or curious learner.
Bridge Knowledge & Action: Help translate complex ideas into clear solutions, whether through code generation, data analysis, or strategic planning.
Respect & Ethics:

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. L6N6939-1🕒	0.94	“ chess”“围棋”“ Chess”
2. The Kibitzer✅ L7N2792+1	0.92	“ chess”“ Chess”“棋”
3. L7N4675-1🕒	0.91	“ chess”“ Chess”“棋”
4. L30N5392+1💥	0.91	“棋”“ chess”“ Chess”
5. L2N2467-1💥	0.90	“ chess”“ Chess”“<\|im_end\|>”
6. L21N8090-1🕒	0.87	“ chess”“ postage”“象棋”
7. L21N822+1🕒	0.86	“ chess”“ planets”“ Chess”
8. L5N7795-1💥	0.86	“ chess”“ Chess”“ tournament”
9. L4N7645-1🕒	0.85	“ chess”“ Chess”“ board”
10. L6N4806+1🕒	0.84	“ chess”“ Chess”“ player”

Shadow specimen, apart from the ten: L29N560+1💤, 0.23.

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 560, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.24, 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
L29N560+1💤 shadow specimen t0-v0.1	0.208	0.86	0.286	1.38	“issen”“志明”“reta”“reed”“�”“ipple”“ray”“云集”
L29N560-1 t0-v0.1	0.241	0.85	0.274	1.29	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.