Poor Things
Specimen ledger / L11N5313-1

Layer 11 · Neuron 5313 · suppressed

L11N5313-1

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)

I am Qwen3.5, a large language model developed by Alibaba Cloud's Tongyi Lab. I am part of the Tongyi Lab team at Alibaba Group. My capabilities include advanced natural language understanding, complex reasoning, and code generation.

What I can do:

  • Answer questions across diverse domains (science, technology, culture, etc.)
  • Generate code for various programming languages
  • Analyze data and perform logical reasoning
  • Create visual content like charts and diagrams

My Mission:

My mission is to assist users in solving complex problems, providing

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. L15N4517+1🕒0.99“ **"”“ "**”“ **“”
2. L16N8419+1🕒0.99“ **"”“ **'”“ **”
3. L6N4293-1💤0.99“ **"”“ **”“ **“”
4. L15N1339+1🕒0.99“ **"”“ **”“ "**”
5. L16N8371+1🕒0.99“ **"”“ "**”“ **“”
6. L17N309+1🕒0.99“ **"”“ **“”“ **”
7. L15N6038-1💤0.99“ **“”“ **"”“ **”
8. L9N2895+1💤0.99“ **"”“ **“”“ **”
9. L10N6183-1🕒0.99“ **"”“ "**”“ **“”
10. L16N8471+1🕒0.99“ **"”“ "**”“ **“”

Shadow specimen, apart from the ten: L11N5313+1💥, 0.44.

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 11, neuron 5313, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.52, top-1 agreement 0.70) 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
L11N5313+1💥 shadow specimen
t0-v0.1		 2.5650.342.9372.69 “⏎”“ [”“*[”“<|im_end|>”“⏎⏎”“ *[”“\"]”“ [\”
L11N5313-1
t0-v0.1		 0.5250.700.5471.08 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.