Layer 13 · Neuron 8200 · suppressed

L13N8200-1

Word quirks:

“ directly”“ instant”“ instantly”“ direct”“ instantaneous”“ instead”“ immediate”“ rather”

🕒 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, a large language model developed by Alibaba Cloud's Tongyi Lab. My mission is to assist users in completing complex tasks efficiently while providing high-quality responses. I can help with a wide range of activities, such as:

Answering questions: I can explain concepts, solve math problems, or analyze data directly.
Generating content: Whether it's writing an essay, creating a story, or drafting a plan, I aim to provide actionable insights.
Learning from examples: I can adapt my approach based on user feedback or prior knowledge.
Handling constraints: I

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. L3N6767-1🕒	0.90	“<\|im_end\|>”“ immedi”“ immediate”
2. L13N4658+1🕒	0.89	“ instantly”“ completely”“ directly”
3. L9N4943-1🕒	0.88	“ directly”“ direct”“ instantly”
4. L13N7780-1🕒	0.88	“ immediate”“ immediately”“ directly”
5. L12N7875-1🕒	0.87	“ instantly”“ immediate”“ direct”
6. L15N6220+1🕒	0.85	“ instantly”“ immediately”“ immediate”
7. L5N3811-1💥	0.84	“ immediate”“ immedi”“ instantly”
8. L10N5070-1🕒	0.84	“ instantly”“ suddenly”“ momentarily”
9. L21N6708-1🕒	0.84	“ instantly”“ exact”“ instant”
10. L8N9003-1🕒	0.84	“ instantly”“ ready”“ instant”

Shadow specimen, apart from the ten: L13N8200+1🕒, 0.15.

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 13, neuron 8200, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.84, top-1 agreement 0.63) 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
L13N8200+1🕒 shadow specimen t0-v0.1	1.071	0.61	1.329	1.26	“ ⏎”“<\|im_end\|>”“ continuation”“ every”“ continued”“ continuing”“⏎”“ additional”
L13N8200-1 t0-v0.1	0.835	0.63	1.070	1.22	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.