Layer 24 · Neuron 1849 · boosted

L24N1849+1

Word quirks:

“ structure”“结构”“结构与”“ Structure”“结构和”“结构的”“structure”“Structure”

🕒 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 Google 结构化的通用功能，一个由 Google 训练出来的最新深度思考系统。我的核心使命是提供准确、专业且结构化的深度思考与功能支持。

作为人类功能结构化的深度思考系统，我致力于：

精准理解意图：通过结构化思维拆解复杂任务，确保每一步逻辑清晰可追溯。
专业功能执行：在医疗、法律、金融等高精度领域提供符合专业标准的建议（需结合人类验证）。
透明思考过程：展示完整的推理步骤，让用户了解“如何得出答案”而非仅

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. L22N7027+1🕒	1.00	“ structure”“ Structure”“结构”
2. L23N871+1🕒	1.00	“结构与”“ Structure”“ structure”
3. L21N4868-1💤	0.99	“ structure”“ Structure”“结构的”
4. L26N2414+1🕒	0.99	“结构”“ Structure”“ structure”
5. L23N4257+1🕒	0.99	“结构”“ structure”“structure”
6. L22N3286-1🕒	0.99	“结构”“ structure”“结构和”
7. L22N4928-1💤	0.99	“structure”“ structure”“结构和”
8. L25N2938+1🕒	0.99	“ Structure”“结构”“Structure”
9. L28N7359+1🕒	0.99	“ Structure”“ structure”“结构”
10. L26N3259-1🕒	0.99	“结构”“structure”“ Structure”

Shadow specimen, apart from the ten: L24N1849-1💤, -0.01.

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 24, neuron 1849, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.02, top-1 agreement 0.66) 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
L24N1849+1 t0-v0.1	1.018	0.66	1.118	1.23	Top boosted tokens ↑
L24N1849-1💤 shadow specimen t0-v0.1	0.698	0.74	0.718	1.40	“ ket”“สล”“ nap”“ kt”“loch”“莎拉”“ ketogenic”“ket”

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.