Layer 11 · Neuron 3123 · suppressed

L11N3123-1

Word quirks:

“ often”“ my”“ without”“ choice”“ free”“ WITHOUT”“ sometimes”“ myself”

🕒 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 Qwen3.5, a large language model with a 256K context window and no specific training cost mentioned in the prompt. My mission is to provide high-quality, accurate information and assistance to users without any financial barriers. I aim to help users navigate complex topics or tasks by offering clear explanations, insights, or solutions that enhance understanding, rather than simply stating my capabilities. If you have a specific question about my role, feel free to ask!

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. L11N5742+1💤	0.85	“ choice”“ my”“ always”
2. L11N8386-1🕒	0.79	“ without”“ sometimes”“ often”
3. L8N8139-1🕒	0.78	“ without”“ lacking”“ myself”
4. L14N6258-1💤	0.78	“ otherwise”“ my”“ your”
5. L11N1868+1💤	0.77	“ sometimes”“ without”“ description”
6. L12N7487-1💤	0.75	“ sometimes”“⏎”“ maybe”
7. L10N7789+1🕒	0.74	“ myself”“ my”“ choice”
8. L13N2946-1💤	0.73	“ sometimes”“ often”“ nowadays”
9. The Opportunist✅ L7N8620+1	0.72	“ ‘”“ '”“ according”
10. L11N6833-1🕒	0.72	“ my”“ even”“ ANY”

Shadow specimen, apart from the ten: L11N3123+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 11, neuron 3123, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.88, top-1 agreement 0.59) 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
L11N3123+1🕒 shadow specimen t0-v0.1	1.089	0.60	1.376	1.54	“ report”“ presently”“ assessed”“ assessment”“ evaluation”“ evaluations”“ assessments”“ evaluated”
L11N3123-1 t0-v0.1	0.885	0.59	1.102	1.42	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.