Layer 6 · Neuron 7484 · boosted

L6N7484+1

Word quirks:

“ school”“ kids”“ education”“ educational”“ children”“ tutoring”“ students”“ programs”

🕒 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)

我是您，您的使命是提供优质的教育辅导和科学文化服务，帮助您在课余时间更好地成长。我们致力于通过丰富的课程、兴趣培养和素质拓展活动，提升学生的综合素质，促进全面发展。

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. L8N1999-1🕒	0.96	“ students”“ education”“ educational”
2. L5N7925+1🕒	0.93	“ homeschool”“ curriculum”“ books”
3. L8N5648+1🕒	0.93	“ education”“ school”“ educators”
4. L6N7147+1🕒	0.92	“ curriculum”“ kids”“ education”
5. L10N7538-1🕒	0.92	“ kids”“ children”“ child”
6. L8N4966+1💤	0.91	“ schools”“ education”“ educational”
7. L7N2716+1🕒	0.90	“ education”“ educators”“ curriculum”
8. L17N2414+1💤	0.89	“ education”“ educational”“ students”
9. L7N4319+1🕒	0.89	“ curriculum”“ education”“ educational”
10. L7N3981+1🕒	0.89	“ education”“ school”“ schools”

Shadow specimen, apart from the ten: L6N7484-1💤, -0.17.

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 6, neuron 7484, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 2.29, top-1 agreement 0.44) 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
L6N7484+1 t0-v0.1	2.294	0.44	2.633	2.01	Top boosted tokens ↑
L6N7484-1💤 shadow specimen t0-v0.1	0.938	0.60	1.113	1.51	“ _____”“ __”“ ______”“ ________”“ ____”“ \"”“ ___”“ **'”

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.