Specimen ledger / L5N5518-1

Layer 5 · Neuron 5518 · suppressed

L5N5518-1

Word quirks:

“ “”“ ‘”““”“ (“”“ **“”“：“”“，“”“‘”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

这是一个非常经典的面试自我介绍或求职信中的核心问题，通常出现在公务员、事业单位或大型国企的笔试环节。

由于我是一个人工智能助手，我无法提供具体的“人”和“事”，但我可以为你详细解析这个问题的含义、考察点以及回答思路。

1. 问题的含义与背景

这句话通常出现在结构化面试（如国考、省考）中，属于第一题或第二题（言语理解与表达模块）。

考察内容：主要考察考生的逻辑思维能力、语言组织能力

The AI judge wasn't sure this holds together.

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. L4N4074-1💤	1.00	“ “”““”“ ‘”
2. L14N74-1💥	0.98	“ “”““”“ ‘”
3. L16N685-1🕒	0.98	“ ‘”“ “”“‘”
4. L9N5006-1💤	0.98	“ “”““”“ **“”
5. L5N4782-1💤	0.98	““”“ “”“ ‘”
6. L16N1247+1🕒	0.98	““”“ “”“ ‘”
7. L5N1006-1💤	0.98	“ ‘”“ “”““”
8. L6N1698+1💤	0.98	“ “”“ ‘”“ (“”
9. L5N7547-1🕒	0.98	“ “”“ **“”““”
10. L4N889+1🕒	0.98	“ ‘”“ “”“ (“”

Shadow specimen, apart from the ten: L5N5518+1💥, 0.27.

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 5, neuron 5518, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.72, top-1 agreement 0.68) 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
L5N5518+1💥 shadow specimen t0-v0.1	10.676	0.00	11.331	4.16	“来”“。”“在”“问题”“被”“需要”“去”“关于”
L5N5518-1 t0-v0.1	0.717	0.68	0.826	1.41	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.