Layer 13 · Neuron 2858 · boosted

L13N2858+1

Word quirks:

“...””“<|im_end|>”“……”“ ____”“ ‘”“ ______”“ ...”“⏎”

💤 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, the latest large language model developed by Alibaba Cloud's Tongyi Lab. My capabilities span advanced reasoning, code generation, and multilingual support, enabling me to assist with complex problem-solving across various domains. I leverage cutting-edge architecture and training techniques to ensure high accuracy and efficiency in handling diverse tasks. If you have specific requirements or preferences for future iterations, please let me know! 😊

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. The Ventriloquist✅ L10N8698+1	0.96	“ ______”“⏎”“<\|im_end\|>”
2. L5N4129+1🕒	0.96	“⏎”“<\|im_end\|>”“ ‘”
3. L7N3811-1💤	0.95	“⏎”“<\|im_end\|>”“...””
4. L3N3940-1⛔	0.95	“<\|im_end\|>”“⏎”“...””
5. L6N1792-1💤	0.94	“<\|im_end\|>”“ _____”“ ‘”
6. L16N2548-1🕒	0.94	“...””“...”“ such”
7. L5N9173-1🕒	0.93	“<\|im_end\|>”“ ‘”“…”
8. L11N712-1🕒	0.93	“<\|im_end\|>”“...\”“ ____”
9. L9N1773-1🕒	0.93	“ ‘”“⏎”“……”
10. L5N3016+1💤	0.93	“...””“ ‘”“...”

Shadow specimen, apart from the ten: L13N2858-1🕒, -0.07.

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 2858, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.71, top-1 agreement 0.69) 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
L13N2858+1 t0-v0.1	0.712	0.69	0.895	1.35	Top boosted tokens ↑
L13N2858-1🕒 shadow specimen t0-v0.1	0.881	0.68	1.011	1.29	“ sometimes”“ safety”“ observation”“ "**”“ usually”“ protected”“ often”“ initially”

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.