Layer 12 · Neuron 8478 · suppressed

L12N8478-1

Word quirks:

“<|im_end|>”“⏎”“⏎⏎”“ ***”“⏎⏎⏎”“ here”“.:”“:\”

🕒 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 with advanced capabilities in understanding complex tasks, analyzing visual information, and performing logical reasoning. My mission is to provide high-quality, accurate, and efficient assistance across a wide range of domains, ensuring that users can rely on my knowledge and skills for any task they need help with. Whether it's answering questions, solving problems, or generating content, I aim to deliver the most accurate and up-to-date information possible to support users effectively. This ensures that users can rely on my knowledge and skills for any task they need help with.
</think>

I am **Qwen3.

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. L12N1099+1🕒	0.89	“<\|im_end\|>”“⏎⏎”“:”
2. L10N3302-1🕒	0.88	“<\|im_end\|>”“⏎”“⏎⏎”
3. L16N5339+1💤	0.88	“⏎⏎”“<\|im_end\|>”“ **”
4. L1N1196-1💥	0.87	“<\|im_end\|>”“⏎⏎”“⏎”
5. L6N7971-1💤	0.87	“<\|im_end\|>”“⏎⏎”“⏎”
6. L10N3698-1💤	0.87	“⏎”“⏎⏎”“⏎⏎⏎”
7. L7N1068-1🕒	0.87	“<\|im_end\|>”“⏎”“⏎⏎”
8. L2N1727-1🕒	0.87	“<\|im_end\|>”“⏎”“⏎⏎”
9. L1N611+1💥	0.87	“<\|im_end\|>”“⏎”“⏎⏎”
10. L2N1259+1💥	0.87	“<\|im_end\|>”“⏎”“.:”

Shadow specimen, apart from the ten: L12N8478+1🕒, 0.59.

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 8478, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.85, top-1 agreement 0.62) 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
L12N8478+1🕒 shadow specimen t0-v0.1	0.857	0.64	1.107	1.21	“<\|im_end\|>”“⏎”“ ⏎”“ ⏎”“ ⏎⏎”“ typically”“ ⏎⏎”“ separated”
L12N8478-1 t0-v0.1	0.852	0.62	1.146	1.52	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.