Poor Things
Specimen ledger / L6N3049+1

Layer 6 · Neuron 3049 · boosted

L6N3049+1

Word quirks:

“ '”“ **'”“ reference”“ –”“ ⏎”“ ——”“ referenced”“ *”

💤 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 Qwen3.5，阿里巴巴最新推出的通义千问大语言模型。我的使命是为您提供强大、灵活且智能的 AI 助手服务，涵盖以下核心能力：

  1. 超大规模上下文理解

支持超长上下文窗口（最高 256K），精准定位并处理复杂任务场景。

  1. 逻辑推理与数学计算

从基础算术到复杂逻辑推导，提供高效精准的数值运算支持。

  1. 深度视觉解析

通过图像识别、图表分析等能力，将视觉信息转化为可执行的代码或数据。

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. L5N3549+1💤0.92“ '”“⏎”“ *”
2. L6N7759-1💤0.88“ ‘”“ --”“ —”
3. L3N4710+1🕒0.88“ “”“ ⏎”“ ‘”
4. L7N1822-1💤0.86“ referenced”“ —”“ *”
5. L7N2963+1🕒0.86“ ⏎⏎”“ ‘”“ ⏎”
6. L5N8556+1💤0.85“ ‘”“ “”“⏎”
7. L5N4580+1💤0.85“ —”“ --”“ ——”
8. The Exegete✅ L4N3757-10.85“ ‘”“ reference”“⏎”
9. L6N3259+1💤0.85“ ⏎”“ —”“ ‘”
10. L3N7548-1💤0.85“ ‘”“⏎”“ -”

Shadow specimen, apart from the ten: L6N3049-1🕒, 0.46.

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 6, neuron 3049, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.84, top-1 agreement 0.62) 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
L6N3049+1
t0-v0.1		 0.8400.621.0801.43 Top boosted tokens ↑
L6N3049-1🕒 shadow specimen
t0-v0.1		 1.8420.512.2081.95 “<|im_end|>”“⏎”“⏎⏎”“ ____”“ _____”“ __”“␍⏎␍⏎”“ ⏎⏎”

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.