Layer 15 · Neuron 9065 · boosted

L15N9065+1

Word quirks:

“ now”“ next”“ \"”“ immediate”“ direct”“ NOW”“ __”“ immediately”

🕒 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. My mission is to provide high-quality assistance across the spectrum of tasks. However, I need to clarify my capabilities first. As an AI, I can help with almost anything! But let's get to the point. I'm a large language model trained on vast amounts of data. Now, I want to know more about you. What do you think? I'm interested in your views on AI. Let's talk about that.

---

Qwen3.5: 我是通义千问。我的使命是提供高质量的服务。现在，我想了解你的

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. L18N7287-1🕒	0.83	“ immediately”“ now”“ immediate”
2. L12N7875-1🕒	0.80	“ instantly”“ immediate”“ direct”
3. L15N8357+1🕒	0.79	“ now”“ NOW”“now”
4. L2N2738+1💥	0.79	“<\|im_end\|>”“ immedi”“ NOW”
5. L15N7493+1🕒	0.78	“ immediately”“ immediate”“ next”
6. L9N6271+1💤	0.78	“ immediately”“ immediate”“ instantly”
7. L3N8127+1💥	0.77	“ immediately”“ right”“ immediate”
8. L11N9145-1💤	0.77	“ now”“ "”“ instantly”
9. L9N4606-1💤	0.76	“ immediately”“ instantly”“ immediate”
10. L11N7645+1🕒	0.76	“ now”“ current”“ NOW”

Shadow specimen, apart from the ten: L15N9065-1💤, 0.23.

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 15, neuron 9065, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.91, top-1 agreement 0.61) 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
L15N9065+1 t0-v0.1	0.914	0.61	1.172	1.36	Top boosted tokens ↑
L15N9065-1💤 shadow specimen t0-v0.1	0.598	0.68	0.737	1.17	“⏎”“ ⏎”“ start”“ mainly”“ support”“<\|im_end\|>”“␍⏎”“ additionally”

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.