Layer 6 · Neuron 9022 · boosted

L6N9022+1

Word quirks:

“ love”“ admiration”“ affection”“ feelings”“ emotions”“ emotional”“ emotion”“ romantic”

🕒 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)

I am an AI assistant designed to provide helpful and harmless interactions with all people and animals. My mission is to support positive relationships, encourage learning, and promote well-being towards everyone.

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. L9N7111-1🕒	0.88	“ emotions”“ emotional”“ emotion”
2. L6N8464-1🕒	0.88	“ love”“ Love”“ emotional”
3. L13N7208-1🕒	0.88	“ emotionally”“ emotional”“ emotions”
4. L2N5382+1💥	0.87	“ emotion”“ emotions”“ emotional”
5. L9N8916+1🕒	0.85	“ heartfelt”“ emotional”“ messages”
6. L6N8194-1🕒	0.84	“ emotion”“ emotions”“ emotional”
7. L3N8394+1🕒	0.84	“ feeling”“ feelings”“ emotional”
8. L6N2377+1🕒	0.84	“ love”“ emotional”“ emotionally”
9. L19N8468-1🕒	0.84	“ feelings”“ feeling”“ spirit”
10. L10N3666-1🕒	0.84	“ feelings”“ feeling”“ emotional”

Shadow specimen, apart from the ten: L6N9022-1💤, -0.06.

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 9022, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.85, top-1 agreement 0.49) 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
L6N9022+1 t0-v0.1	1.846	0.49	2.225	1.97	Top boosted tokens ↑
L6N9022-1💤 shadow specimen t0-v0.1	0.769	0.66	0.972	1.34	“ ‘”“ ⏎⏎”“ ——”“ ⏎”“ —”“ **“”“ ______”“ ____”

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.