Layer 7 · Neuron 2824 · suppressed

L7N2824-1

Word quirks:

“ ‘”“ ””“ ⏎”“‘”“ ⏎”“ “”“ myself”“ ‘’”

🕒 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 Qwen3.5，一个由阿里巴巴研发的超大规模语言模型。我的使命是协助人们高效、安全地完成各类任务，包括处理复杂的数学问题、分析数据背后的规律，以及生成高质量的文本、图像和音频内容。

核心能力：

数学计算：能够解析代数表达式、几何图形，并执行精确的数值运算。
数据分析：通过统计方法（如均值 - 方差分析）揭示数据分布特征，结合可视化技术（如直方图）呈现数据与变量之间的关系。
内容创作：利用算法生成艺术性强的文本

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. L10N718+1💤	0.97	“ ‘”“ ‘’”“ “”
2. L7N3546-1💤	0.97	“ ‘”“ ””“⏎”
3. L3N780+1💤	0.97	“ ‘”“ ⏎”“⏎”
4. L14N7717-1💤	0.96	“ ‘”“ “”“ ⏎”
5. L3N610+1💤	0.96	“ ‘”“ ””“ ‘’”
6. L3N7846-1💤	0.96	“ ‘”“‘”“ ””
7. L7N3866+1🕒	0.96	“ ‘”“⏎”“ ⏎”
8. L2N6902+1🕒	0.96	“ ‘”“ ‘’”“ ””
9. L3N3514+1💤	0.96	“ ‘”“ ””“ “”
10. L8N2027+1🕒	0.96	“ ‘”“ “”“ ””

Shadow specimen, apart from the ten: L7N2824+1💥, -0.13.

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 2824, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.11, 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
L7N2824+1💥 shadow specimen t0-v0.1	2.571	0.37	2.957	2.35	“ word”“ words”“ meaning”“ Greek”“ verb”“ meanings”“ translation”“ translated”
L7N2824-1 t0-v0.1	1.110	0.66	1.261	1.34	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.