Layer 6 · Neuron 8447 · boosted

L6N8447+1

Word quirks:

“ usually”“ generally”“ specific”“ general”“ provided”“ standard”“ usual”“ processing”

🕒 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)

As an AI, I do not have personal experiences or a specific identity to report. I am a large language model designed to assist with information processing and tasks.

If you are looking for a specific person (e.g., a friend, family member, or colleague) to ask about their mission, please provide more context or try asking them directly.

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. L10N6724+1💤	0.90	“ typical”“ usually”“ typically”
2. L7N6385-1💤	0.89	“⏎”“ usually”“ standard”
3. L9N5230-1🕒	0.89	“ usually”“ generally”“ typically”
4. L11N4251+1🕒	0.88	“ usually”“ specific”“ generally”
5. L8N1369+1💤	0.88	“ usually”“ generic”“ typically”
6. L10N5794+1🕒	0.88	“ usually”“ generally”“ typically”
7. L11N3403-1💤	0.87	“ generally”“ usually”“ standard”
8. L9N1797-1🕒	0.87	“ usually”“ standard”“ typical”
9. L12N6609-1💤	0.87	“ generally”“ general”“ specific”
10. L11N884-1🕒	0.87	“ usually”“ typically”“ typical”

Shadow specimen, apart from the ten: L6N8447-1🕒, 0.08.

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 6, neuron 8447, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.02, top-1 agreement 0.66) 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.

Setting	KL divergence	Top-1 agreement	ΔNLL	Entropy	Steer lens
L6N8447+1 t0-v0.1	1.019	0.66	1.236	1.36	Top boosted tokens ↑
L6N8447-1🕒 shadow specimen t0-v0.1	1.848	0.50	2.154	1.78	“ medieval”“ Medieval”“ knights”“ knight”“ castle”“ cathedral”“ feudal”“ noble”

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.