Specimen ledger / L13N4012+1

Layer 13 · Neuron 4012 · boosted

L13N4012+1

Word quirks:

“ similar”“ response”“ visually”“ layers”“ similarly”“ generating”“ follow”“ corresponding”

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

Identity (according to the specimen itself)

I am an AI assistant. I will introduce myself and my mission as follows:

Self-introduction: I will introduce myself and my mission.
Response to the user's request: I will respond to the user's request.

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. L11N3162-1🕒	0.79	“ corresponding”“ generating”“ energy”
2. L9N857-1💤	0.75	“ similar”“ directly”“ related”
3. L16N3139-1💤	0.74	“ similarly”“ similar”“ nearby”
4. L11N3487-1🕒	0.73	“ similar”“ similarly”“ corresponding”
5. L10N5747-1🕒	0.73	“ similar”“ now”“ similarly”
6. L10N5417-1🕒	0.73	“ corresponding”“ similarly”“ analogous”
7. L14N9165+1💤	0.73	“ similar”“ similarly”“ analogous”
8. L13N7022-1💤	0.73	“ similar”“ corresponding”“ similarly”
9. L16N8053-1💤	0.73	“ similar”“ similarly”“ analogous”
10. L15N1963+1💤	0.73	“ similar”“ analogous”“ similarly”

Shadow specimen, apart from the ten: L13N4012-1🕒, 0.11.

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 13, neuron 4012, 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
L13N4012+1 t0-v0.1	1.178	0.64	1.467	1.33	Top boosted tokens ↑
L13N4012-1🕒 shadow specimen t0-v0.1	0.810	0.67	0.920	1.24	“ crafted”“ here”“ discussed”“ [”“ your”“ mentioned”“ showcased”“ *[”

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.