Layer 12 · Neuron 9214 · suppressed

L12N9214-1

Word quirks:

“ my”“ I”“<|im_end|>”“ myself”“!”“ requested”“ you”“ your”

🕒 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. My mission is to assist users with their tasks, whether it's answering questions, writing code, or generating creative content. How can I help you today?

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. L7N6197+1🕒	0.89	“<\|im_end\|>”“ myself”“ you”
2. L13N7013-1🕒	0.88	“ yours”“ my”“ myself”
3. L8N7306-1🕒	0.86	“<\|im_end\|>”“ myself”“ response”
4. The Confessor✅ L9N1211+1	0.85	“ my”“ I”“ myself”
5. L6N4116-1🕒	0.85	“ you”“ me”“ YOU”
6. L7N7340+1💤	0.85	“ my”“ your”“ I”
7. L6N5656-1🕒	0.84	“ YOU”“<\|im_end\|>”“ you”
8. L5N7559+1🕒	0.84	“ my”“ your”“ myself”
9. L12N6414-1💤	0.83	“ my”“ multiple”“ your”
10. L7N1739+1💤	0.83	“ your”“ my”“⏎”

Shadow specimen, apart from the ten: L12N9214+1🕒, 0.08.

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 12, neuron 9214, 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 0.64) 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
L12N9214+1🕒 shadow specimen t0-v0.1	1.054	0.58	1.335	1.95	“<\|im_end\|>”“?\”“?”“?!”“?</”“?"”“?...”“?:”
L12N9214-1 t0-v0.1	0.908	0.64	1.116	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.