Layer 17 · Neuron 1145 · boosted

L17N1145+1

Word quirks:

“ together”“ they”“ differing”“ pair”“ They”“ their”“ both”“ alike”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

I am Qwen3.5, a large language model developed by Tongyi Lab. My mission is to assist users through the following goals:

Answer questions: Provide accurate, relevant information across diverse topics (e.g., science, history, technology).
Solve problems: Offer step-by-step reasoning for math, logic, or coding tasks.
Create content: Generate stories, articles, code, or creative works tailored to user needs.
Support workflows: Optimize efficiency via task automation, data analysis, or project planning.
**

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. L13N4831-1💤	0.82	“ similar”“ them”“ their”
2. L17N4304-1💤	0.80	“ themselves”“ their”“ they”
3. L16N4689+1💤	0.80	“ both”“ different”“ theirs”
4. L14N7030-1🕒	0.79	“ themselves”“ them”“ they”
5. L14N120+1💤	0.76	“ combined”“ together”“—they”
6. L12N6872-1🕒	0.76	“ their”“ they”“ They”
7. L15N494-1💤	0.75	“ related”“ both”“ yourself”
8. L14N5081+1🕒	0.75	“ ones”“ each”“ are”
9. L15N3721+1💤	0.74	“ these”“ These”“ them”
10. L16N4807-1🕒	0.74	“ themselves”“ they”“ their”

Shadow specimen, apart from the ten: L17N1145-1🕒, 0.37.

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 17, neuron 1145, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.45, top-1 agreement 0.78) 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
L17N1145+1 t0-v0.1	0.450	0.78	0.530	1.07	Top boosted tokens ↑
L17N1145-1🕒 shadow specimen t0-v0.1	0.906	0.63	1.093	1.45	“ another”“ quieter”“ smaller”“ others”“ other”“更小”“ itself”“ probably”

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.