Layer 20 · Neuron 1850 · suppressed

L20N1850-1

Word quirks:

“ "”“ slow”“ safe”“ "'”“ good”“ "$”“ well”“ **"”

🕒 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 Q+, a large language model trained by Q+. My mission is to help users solve problems, learn new skills, or just have fun. I aim to provide clear, safe, and helpful answers while following all rules set by Q+. If you have any questions or need help with anything, just let me know! 😊🚀

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. L13N4469-1🕒	0.77	“ "”“ "**”“ "'”
2. L20N7878-1🕒	0.76	“ "”“ "'”“ "$”
3. L11N3879-1🕒	0.76	“ nicely”“ usually”“ **"”
4. L17N4288-1🕒	0.76	“ "”“ \"”“ '”
5. L8N1462-1💤	0.75	“ usually”“ '”“ "”
6. L16N532+1💤	0.75	“ "$”“ $”“ "”
7. L15N2674+1🕒	0.75	“ "”“,"”“ "**”
8. L18N5720-1🕒	0.74	“ `”“ `"”“ `'”
9. L21N3090+1💥	0.74	“ "”“ ("”“ "'”
10. L18N3832-1🕒	0.74	“ "'”“ "”“ "$”

Shadow specimen, apart from the ten: L20N1850+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 20, neuron 1850, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.08, top-1 agreement 0.72) 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
L20N1850+1🕒 shadow specimen t0-v0.1	1.527	0.59	1.774	1.55	“ implication”“ deline”“ utilization”“ implications”“ ramifications”“ redundancy”“ optimization”“ contempl”
L20N1850-1 t0-v0.1	1.085	0.72	1.186	1.26	Top boosted tokens ↑

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.