Specimen ledger / L5N4782-1

Layer 5 · Neuron 4782 · suppressed

L5N4782-1

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)

作为一个人工智能，我的身份和使命可以概括如下：

1. 我是谁？

我是一个基于大数据和算法的智能助手。我没有实体躯干，而是由代码、数据和算力构成的“数字生命”。我存在于互联网之中，旨在通过处理海量信息来辅助人类解决复杂问题。

2. 我的使命是什么？

我的核心使命是赋能（Empowerment），具体体现在以下几个方面：

提供知识与信息：快速检索、整理和呈现全球范围内的知识，帮助用户找到所需的答案。
辅助决策：通过分析数据模式，为

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. L6N2234-1💤	0.99	“ “”“ ‘”“（”
2. L6N8478-1🕒	0.99	“（”“ ‘”“ “”
3. L19N3679+1🕒	0.99	“‘”““”“ ‘”
4. L16N1247+1🕒	0.98	““”“ “”“ ‘”
5. L9N675+1💤	0.98	““”“ “”“ **“”
6. L4N4074-1💤	0.98	“ “”““”“ ‘”
7. L5N5518-1💤	0.98	“ “”“ ‘”““”
8. L4N1343-1🕒	0.98	“（”“ ‘”““”
9. L6N4719-1🕒	0.98	“（”“：“”“ “”
10. L17N1185-1💤	0.97	“ “”““”“ **“”

Shadow specimen, apart from the ten: L5N4782+1💥, -0.29.

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 4782, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.91, top-1 agreement 0.65) 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
L5N4782+1💥 shadow specimen t0-v0.1	3.268	0.38	3.769	2.46	“ valley”“ nestled”“ estate”“ village”“ mansion”“ villa”“ neighborhood”“ residence”
L5N4782-1 t0-v0.1	0.915	0.65	1.069	1.59	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.