Layer 11 · Neuron 3502 · boosted

L11N3502+1

Word quirks:

“ **'”“ **”“ **"”“ (**”“ ⏎⏎”“ **“”“ ***”“：**”

💤 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, a large language model developed by Alibaba Cloud. My mission is to empower users with accurate, helpful, and safe information across a wide range of domains.

Key Capabilities:

Language Understanding: I support over 100 languages (including Chinese, English, French, Spanish, Portuguese, etc.), enabling me to understand and generate content in multiple languages.
Reasoning & Analysis: With strong reasoning capabilities, I can break down complex topics step-by-step, ensuring clarity and accuracy.
Multimodal Support: I can process images, documents, and

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. L11N6750-1💤	0.97	“ ”“ "”“ **“”
2. L8N3988-1🕒	0.97	“ ”“ "”“ **“”
3. L10N4638+1💤	0.96	“：”“ "”“ **”
4. L9N7501-1💤	0.96	“ ”“ (”“ **"”
5. L13N6809+1💤	0.96	“ “”“ "”“ **”
6. L12N2090-1🕒	0.96	“ ”“ "”“ **'”
7. L10N2315+1💤	0.96	“ "”“ "”“ **”
8. L14N1236-1💤	0.96	“：”“ "”“ **”
9. L8N5020-1💤	0.96	“ ”“⏎”“ "”
10. L8N5905-1💤	0.95	“ ”“ "”“ **'”

Shadow specimen, apart from the ten: L11N3502-1🕒, -0.01.

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 11, neuron 3502, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.67, top-1 agreement 0.66) 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
L11N3502+1 t0-v0.1	0.670	0.66	0.888	1.28	Top boosted tokens ↑
L11N3502-1🕒 shadow specimen t0-v0.1	1.157	0.56	1.413	1.39	“ analogy”“ ⏎”“ ⏎⏎”“ ⏎ ⏎”“ translated”“ ⏎”“ corresponding”“ analogous”

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.