Layer 7 · Neuron 312 · boosted

L7N312+1

Word quirks:

“ "”“ **“”“ **"”“ “”“ '”“ ‘”“ *“”“ actually”

💤 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, a large-scale AI model developed by Alibaba Cloud. My mission is to provide high-quality, accurate, and helpful information across a wide range of topics, including but not limited to:

Technology & Innovation: Explaining the latest advancements in AI, quantum computing, and related fields.
Scientific Research: Assisting researchers in understanding complex theories and their implications.
Educational Content: Helping students and learners grasp fundamental concepts through clear explanations and examples.
Practical Applications: Offering actionable insights for real-world scenarios where these technologies are applied.

If you

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. L5N1050-1💤	0.98	“ ‘”“ “”“ **“”
2. L7N3649+1💤	0.97	“ “”“ ‘”“ \"”
3. L6N4115+1🕒	0.96	“ “”“ **“”“ "”
4. L6N9145+1💤	0.96	“ ‘”“ “”“ \"”
5. L8N7440+1💤	0.96	“ “”“ "”“ ‘”
6. L3N364-1💤	0.96	“ “”“ ‘”“ **“”
7. L6N5324-1💤	0.96	“ **“”“ ‘”“ “”
8. L4N1808+1🕒	0.96	“ “”“ ‘”“ **“”
9. L18N7413+1💤	0.96	“ “”“ “”“ "”
10. L6N8546-1💤	0.96	“ “”“ “”“ "”

Shadow specimen, apart from the ten: L7N312-1🕒, 0.31.

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 7, neuron 312, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.61, top-1 agreement 0.70) 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
L7N312+1 t0-v0.1	0.605	0.70	0.783	1.29	Top boosted tokens ↑
L7N312-1🕒 shadow specimen t0-v0.1	1.038	0.59	1.183	1.17	“⏎”“⏎⏎”“<\|im_end\|>”“.”“⏎ ⏎”“⏎ ⏎”“⏎⏎⏎”“。”

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.