Layer 13 · Neuron 9168 · boosted

L13N9168+1

Word quirks:

“ gradually”“ gradual”“ now”“ progressively”“逐步”“逐渐”“ slowly”“ increasingly”

🕒 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 developed by Alibaba Cloud's Tongyi Lab. My capabilities have evolved over time, with an increased focus on complex reasoning tasks and the ability to handle multimodal inputs. I am designed to assist users in generating content, performing data analysis, and providing more accurate information. How can I assist you today?

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. L1N2844+1💥	0.93	“<\|im_end\|>”“ gradually”“ slowly”
2. L18N8739-1🕒	0.93	“ gradually”“ gradual”“逐步”
3. L17N4698-1🕒	0.92	“ gradual”“ gradually”“ Grad”
4. L20N6271-1🕒	0.92	“ changing”“ progressively”“ gradually”
5. L18N5550+1🕒	0.90	“ gradually”“逐步”“ gradual”
6. The Gradualist✅ L5N3758+1	0.90	“ gradually”“ slowly”“ gradual”
7. L18N7090+1💤	0.89	“ gradually”“ occasional”“逐渐”
8. L12N7600+1🕒	0.88	“ gradually”“ each”“ progressively”
9. L14N5698-1🕒	0.87	“ progressively”“ gradually”“ gradual”
10. L17N5368+1🕒	0.87	“ gradually”“ decreasing”“ progression”

Shadow specimen, apart from the ten: L13N9168-1🕒, 0.31.

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 13, neuron 9168, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.97, top-1 agreement 0.62) 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
L13N9168+1 t0-v0.1	0.968	0.62	1.272	1.13	Top boosted tokens ↑
L13N9168-1🕒 shadow specimen t0-v0.1	0.927	0.62	1.151	1.43	“ still”“ new”“ until”“ newly”“ really”“ till”“ before”“ freshly”

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.