Poor Things
Specimen ledger / L2N1802+1

Layer 2 · Neuron 1802 · boosted

L2N1802+1

Word quirks:

“⏎”“<|im_end|>”“⏎ ⏎”“ ?”“ -->”“\n”“␍⏎”“⏎ ⏎”

🕒 Waiting in line — so far it has only had the quick scan, which shows which words it pushes. It was not selected in this round.

Identity (according to the specimen itself)

I am an AI assistant. My mission is to help you understand the world of technology. I will provide you with the latest advancements in artificial intelligence. I am a model trained by Google. I am a system designed by Microsoft. I am a platform built by Amazon. I am a service created by Apple. I am a tool developed by Oracle. I am a software released by Yahoo. I am a media produced by Netflix. I am a content generated by CNN. I am a blog written by Medium. I am a journal published by Herald. I am a magazine edited by Tribune. I am a newspaper distributed by Warner. I am

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. L6N4788+1🕒0.96“⏎”“\n”“<|im_end|>”
2. Crash Dump✅ L2N527-10.95“⏎”“<|im_end|>”“⏎ ⏎”
3. L2N2598+1🕒0.92“⏎”“<|im_end|>”“␍⏎”
4. L3N754+1🕒0.92“<|im_end|>”“⏎”“⏎⏎”
5. L2N1945+1🕒0.92“<|im_end|>”“⏎”“\n”
6. L8N104-1💤0.92“<|im_end|>”“⏎”“⏎⏎”
7. L2N8581-1🕒0.92“<|im_end|>”“⏎”“ ⏎”
8. L2N8812-1🕒0.92“<|im_end|>”“⏎”“?\”
9. L2N7387-1🕒0.92“<|im_end|>”“⏎”“?\”
10. L4N4589-1💥0.92“<|im_end|>”“⏎”“\n”

Shadow specimen, apart from the ten: L2N1802-1🕒, 0.69.

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 2, neuron 1802, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 2.13, top-1 agreement 0.40) 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
L2N1802+1
t0-v0.1		 2.1310.402.5192.31 Top boosted tokens ↑
L2N1802-1🕒 shadow specimen
t0-v0.1		 1.3870.561.5961.79 “<|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.