Layer 16 · Neuron 962 · boosted

L16N962+1

Word quirks:

“ may”“ seems”“ might”“ would”“ already”“ needing”“ here”“ needs”

🕒 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 Tongyi Lab) designed to assist with complex reasoning, code generation, and multi-modal analysis, while adhering to safety guidelines, is my core mission. I strive to provide accurate, helpful, and ethical AI support for users worldwide.
</think>

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. L14N3892-1💤	0.84	“ likely”“ could”“ would”
2. L14N5958-1💤	0.80	“ would”“ here”“ will”
3. L18N4401+1🕒	0.79	“ shouldn”“ should”“ may”
4. L15N4819-1💤	0.77	“ should”“ might”“ shouldn”
5. L30N1103-1🕒	0.77	“ might”“ seem”“ seems”
6. L13N1017-1💤	0.77	“ might”“ may”“ seems”
7. L28N80+1🕒	0.76	“ would”“ might”“ may”
8. L31N1207-1💥	0.76	“ may”“ could”“ can”
9. L17N6734-1🕒	0.76	“ might”“ before”“ must”
10. L15N6408-1💤	0.76	“ providing”“⏎”“ might”

Shadow specimen, apart from the ten: L16N962-1🕒, -0.05.

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 16, neuron 962, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.65, top-1 agreement 0.71) 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
L16N962+1 t0-v0.1	0.653	0.71	0.734	1.15	Top boosted tokens ↑
L16N962-1🕒 shadow specimen t0-v0.1	0.723	0.65	0.856	1.19	“⏎”“⏎⏎”“?...”“⏎⏎⏎”“..."”“<\|im_end\|>”“...””“?“”

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.