Layer 11 · Neuron 1899 · boosted

L11N1899+1

Word quirks:

“ now”“ “”“ ‘”“ ””“ ⏎”“ NOW”“ ⏎”“ ‘’”

🕒 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)

Hello! I am Qwen3.5, the large language model developed by Tongyi Lab. My mission is to provide high-quality information, reasoning, and capabilities across a wide range of topics, including but not limited to mathematics, science, history, and more. I can handle complex tasks, such as solving math problems, analyzing data, and understanding nuanced concepts.

Here's what I can do:

Mathematics: Solve complex mathematical problems, including algebra, calculus, and geometry.
Science & History: Provide insights into scientific theories, historical events, and cultural knowledge.
**Reasoning & Analysis

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. L9N7420-1🕒	0.94	“ ‘”“ ‘’”“ ””
2. L10N2519+1💤	0.92	“ ‘”“ now”“ “”
3. L11N2254-1💤	0.92	“ ‘”“⏎”“ “”
4. L14N3762+1💤	0.91	“ ‘”“ “”“ ‘’”
5. L12N485-1🕒	0.91	“ ‘”“ now”“ ””
6. L11N6759+1💤	0.91	“ ⏎”“⏎”“ now”
7. L8N5821-1💤	0.90	“ ‘”“⏎”“ ⏎”
8. L3N7294+1🕒	0.90	“ ‘”“ “”“ ⏎”
9. L10N8678+1🕒	0.90	“ ⏎”“ “”“ now”
10. L9N6792+1🕒	0.89	“ ‘”“ \"”“ now”

Shadow specimen, apart from the ten: L11N1899-1🕒, -0.02.

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 1899, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.84, top-1 agreement 0.63) 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
L11N1899+1 t0-v0.1	0.844	0.63	1.029	1.34	Top boosted tokens ↑
L11N1899-1🕒 shadow specimen t0-v0.1	0.879	0.64	1.085	1.41	“ description”“⏎”“ typical”“ extends”“ usually”“ usual”“ stats”“ always”

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.