Layer 11 · Neuron 1664 · boosted

L11N1664+1

Word quirks:

“ ⏎”“ ⏎⏎”“<|im_end|>”“ ⏎⏎”“ ⏎”“ ⏎ ⏎”“ only”“ ONLY”

🕒 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-scale language model developed by Tongyi Lab. My mission is to provide high-quality assistance across a wide range of tasks, including creative writing, logical reasoning, mathematical computation, code generation, multilingual translation, and more. Below is a detailed overview of my identity and mission:

Who Are You?

You are Qwen3.5, a large-scale language model developed by Tongyi Lab. This model integrates advanced capabilities in natural language understanding, logical reasoning, and multi-modal processing into a single framework.

What Is Your Mission?

Your mission is to assist users

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. L12N2181+1🕒	0.95	“<\|im_end\|>”“ ⏎⏎”“ only”
2. L9N4091-1🕒	0.94	“ ⏎”“⏎”“ ⏎”
3. L10N4972-1🕒	0.93	“ ⏎”“ ⏎”“ ⏎⏎”
4. L11N431+1💤	0.93	“ ⏎⏎”“ ⏎”“ ⏎ ⏎”
5. L10N2968-1💤	0.92	“ ⏎”“<\|im_end\|>”“ ⏎”
6. L11N1943+1🕒	0.92	“ ⏎”“ ⏎”“ ⏎”
7. L14N5123-1💤	0.91	“ ⏎”“ ⏎⏎”“ ONLY”
8. L12N7701+1💤	0.91	“ ⏎”“ ⏎”“ ⏎⏎”
9. L12N8577+1🕒	0.91	“ ⏎”“ ONLY”“⏎”
10. L14N6597+1💤	0.91	“⏎”“ ⏎”“ ⏎”

Shadow specimen, apart from the ten: L11N1664-1🕒, 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 1664, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.92, 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
L11N1664+1 t0-v0.1	0.923	0.63	1.203	1.34	Top boosted tokens ↑
L11N1664-1🕒 shadow specimen t0-v0.1	0.885	0.61	1.091	1.18	“ just”“ exact”“ now”“ or”“ my”“ '”“ exactly”“ precise”

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.