Layer 10 · Neuron 6128 · boosted

L10N6128+1

Word quirks:

“ ⏎”“ ⏎”“ ⏎ ⏎”“ ⏎ ⏎”“ ⏎”“ ⏎⏎”“ ␍⏎”“ ⏎ ⏎”

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

Identity (according to the specimen itself)

It seems like you're asking about a specific topic or mission. Could you please clarify which topic or mission you'd like to discuss? I'll do my best to provide relevant information and help where I can.

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. L13N1287+1🕒	1.00	“ ⏎”“ ⏎⏎”“ ⏎⏎”
2. L9N2165+1💤	0.99	“ ⏎”“ ⏎⏎”“ ⏎”
3. L8N4472+1🕒	0.99	“ ⏎”“ ␍⏎”“ ⏎⏎”
4. L9N8272-1🕒	0.99	“ ⏎”“ ⏎⏎”“⏎”
5. L8N6110+1💤	0.99	“ ⏎”“ ⏎”“ ⏎⏎”
6. L18N2155+1💤	0.99	“ ⏎”“ ⏎”“ ␍⏎”
7. L16N1818+1💤	0.99	“ ⏎”“ ⏎⏎”“ ␍⏎”
8. L8N1501+1💤	0.99	“ ⏎”“ ⏎⏎”“ ⏎”
9. L15N4728+1💤	0.99	“ ⏎”“ ⏎⏎”“ ⏎”
10. L16N835+1💤	0.99	“ ⏎”“ ⏎”“ ⏎ ⏎”

Shadow specimen, apart from the ten: L10N6128-1🕒, 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 10, neuron 6128, 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
L10N6128+1 t0-v0.1	1.230	0.59	1.464	1.47	Top boosted tokens ↑
L10N6128-1🕒 shadow specimen t0-v0.1	1.192	0.63	1.495	1.44	“ typically”“ within”“ depiction”“ _____”“ typical”“ ____”“ ______”“ ________”

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.