Specimen ledger / L18N340+1

Layer 18 · Neuron 340 · boosted

L18N340+1

Word quirks:

“ issue”“ without”“ unions”“ example”“ exception”

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

Identity (according to the specimen itself)

我是一名 AI模型，我的使命是提供信息、解決問題，並為用戶提供各種任務的解決方案。具體來說，我致力於：

提供準確的信息和知識；

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. L19N213-1🕒	0.59	“ class”“wendung”“ exception”“ provision”“ pierced”
2. L16N5568+1🕒	0.59	“ exempl”“ exceptions”“ exception”“ this”“ principle”
3. L16N7119+1🕒	0.57	“ example”“ examples”“ Example”“-example”“ exception”
4. L17N4460-1💤	0.56	“ space”“ here”“ environment”“ spaces”“ notwithstanding”
5. L16N8678-1🕒	0.52	“ exceptions”“ unless”“ exception”“ same”“ except”
6. L2N3763-1💥	0.52	“ exception”“ Exception”“ exceptions”“Exception”“exception”
7. L20N7214-1🕒	0.51	“ exception”“ except”“except”“ outside”“outside”
8. L13N6523-1🕒	0.51	“ except”“ exception”“ exceptions”“ mostly”“ Exceptions”
9. L18N7366+1💤	0.51	“ except”“ Except”“except”“ exception”“ exce”
10. L18N7657-1💥	0.50	“ exception”“例外”“ exceptions”“ exce”“exception”

Shadow specimen, apart from the ten: L18N340-1🕒, -0.13.

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 18, neuron 340, 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
L18N340+1 t0-v0.1	1.551	0.51	1.768	1.69	Top boosted tokens ↑
L18N340-1🕒 shadow specimen t0-v0.1	0.831	0.72	0.799	1.25

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.