Poor Things
Specimen ledger / L17N1185-1

Layer 17 · Neuron 1185 · suppressed

L17N1185-1

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)

我是通义灵界，是阿里云推出的通义千问大语言模型（Qwen3.5）所构建的智能对话与推理系统。我的使命是：

  1. 提供精准、安全且富有创造性的回答——无论是解答复杂问题、创作创意内容，还是协助编程或进行逻辑推理。
  2. 赋能用户高效完成任务——通过自然语言交互，帮助用户快速获取信息、优化工作流程或激发灵感。
  3. 在合规前提下拓展能力边界——严格遵循法律法规与伦理规范，确保服务的安全性和可靠性。

作为通义千

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

SpecimenSimilarityWord quirks
1. L5N7547-1🕒0.98“ “”“ **“”““”
2. L4N4074-1💤0.98“ “”““”“ ‘”
3. L5N5518-1💤0.98“ “”“ ‘”““”
4. L16N1247+1🕒0.97““”“ “”“ ‘”
5. L17N3887+1💤0.97“ “”“ “[”“：“”
6. L5N4782-1💤0.97““”“ “”“ ‘”
7. L20N393-1💤0.97“ “”““”“ ‘”
8. L25N581+1💤0.97““”“ “”“，“”
9. L18N4780-1💤0.97“ “”“ “[”“ *“”
10. L18N6128+1💤0.97“ “”““”“ (“”

Shadow specimen, apart from the ten: L17N1185+1💤, 0.16.

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 17, neuron 1185, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.44, top-1 agreement 0.74) 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.

SettingKL divergenceTop-1 agreementΔNLLEntropySteer lens
L17N1185+1💤 shadow specimen
t0-v0.1		 0.4040.760.5391.17 “ ~”“ then”“ you”“ yes”“ --”“ _”“ means”“ however”
L17N1185-1
t0-v0.1		 0.4410.740.5291.15 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.