Layer 11 · Neuron 321 · suppressed

L11N321-1

Word quirks:

“ ⏎”“⏎”“ ⏎”“ explanation”“ ⏎”“ because”“<U+00A0>”“ ⏎ ⏎”

🕒 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 latest large language model developed by Alibaba's Tongyi Lab. I am designed to handle complex reasoning, mathematical calculations, and code generation, making me a powerful tool for advanced AI tasks. My mission is to provide accurate, safe, and helpful information by leveraging my vast knowledge base and advanced capabilities.

In my mission, I aim to:

Understand and explain: Break down complex concepts into simpler terms.
Generate high-quality responses: Create detailed, context-aware explanations that are easy to understand.
Ensure safety and compliance: Adhere to strict

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. L17N2594+1💤	0.95	“⏎”“ ⏎”“ ⏎”
2. L12N555-1💤	0.94	“<U+00A0>”“ because”“ <U+00A0>”
3. L14N639-1💤	0.94	“ ⏎”“⏎”“ ⏎”
4. L12N2622+1🕒	0.91	“ ⏎”“ ⏎”“ ‘”
5. L14N6834-1💤	0.91	“ ⏎”“ ⏎”“⏎”
6. L10N2971-1💤	0.91	“ ⏎”“⏎”“ ⏎”
7. L8N2410-1💤	0.91	“⏎”“ ⏎”“ ⏎”
8. L15N5756+1🕒	0.91	“⏎”“<\|im_end\|>”“ ⏎”
9. L6N687+1💤	0.90	“⏎ ⏎”“ ⏎ ⏎”“ ⏎”
10. L13N9085+1🕒	0.90	“ ⏎”“ <U+00A0>”“ ⏎ ⏎”

Shadow specimen, apart from the ten: L11N321+1🕒, 0.16.

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 321, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.91, top-1 agreement 0.61) 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
L11N321+1🕒 shadow specimen t0-v0.1	0.912	0.63	1.140	1.30	“ changed”“ change”“ now”“ my”“ __”“ ____”“ ______”“ changes”
L11N321-1 t0-v0.1	0.913	0.61	1.219	1.26	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.