Specimen ledger / L1N837-1

Layer 1 · Neuron 837 · suppressed

L1N837-1

Word quirks:

“ tra”“ analyse”“ se”“ ?**”“ !”“<|im_end|>”“ :**”“ que”

🧪 In testing — Answered 0 of 8 prompts so far.

Identity (according to the specimen itself)

The reply didn't hold together

</think>

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. L2N8799+1🕒	0.76	“<\|im_end\|>”“⏎”“ !”
2. L1N2355-1💥	0.73	“<\|im_end\|>”“ ?”“ avec”
3. L1N8120-1💥	0.72	“<\|im_end\|>”“ ?”“ moi”
4. L1N8551+1💥	0.71	“<\|im_end\|>”“ java”“ ?**”
5. L1N2810+1💥	0.71	“<\|im_end\|>”“ ?”“ !”
6. L1N8470-1💥	0.69	“<\|im_end\|>”“ ?**”“ ?”
7. L1N6036+1💥	0.68	“<\|im_end\|>”“ analyse”“ !”
8. L2N1034+1💥	0.68	“ que”“<\|im_end\|>”“ para”
9. L1N8497-1💥	0.68	“ que”“<\|im_end\|>”“ ?”
10. L2N871+1🕒	0.68	“ analyse”“<\|im_end\|>”“⏎”

Shadow specimen, apart from the ten: L1N837+1💥, 0.04.

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 1, neuron 837, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. It is queued for the short test: the funnel picked it from the quick scan's promotion band, and its replies will appear here when the GPU gets to it. 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
L1N837+1💥 shadow specimen t0-v0.1	3.570	0.23	4.079	2.73	“<\|im_end\|>”“⏎”“ ⏎ ⏎”“⏎ ⏎”“⏎ ⏎”“⏎ ⏎”“⏎⏎”“ ⏎”
L1N837-1 t0-v0.1	1.518	0.53	1.817	2.02	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.