Layer 16 · Neuron 9072 · boosted

L16N9072+1

Word quirks:

“ seemingly”“ unseen”“ implicitly”“ logic”“ seems”“ initially”“ you”“ your”

💤 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 primary role is to assist users in completing tasks efficiently and accurately, but I don't have a predefined "mission" in the traditional sense. Instead, my capabilities are designed to align with specific goals based on the context of our interaction. Here's how I approach different scenarios:

Understanding Your Intent: When you ask a question or provide a task, I analyze the information you've given me to identify the core requirements. For example, if you mention a specific topic (like coding), I might focus on generating code that fits

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. The Therapist✅ L10N6316-1	0.81	“ seeming”“ unknown”“ you”
2. L15N7800-1🕒	0.76	“ your”“ seems”“ you”
3. L18N4127-1🕒	0.76	“ your”“ seeming”“ trying”
4. L11N1291-1🕒	0.74	“ probably”“ maybe”“ seems”
5. L14N5851-1🕒	0.74	“ seems”“ seeming”“ yourself”
6. L14N6680+1💤	0.74	“ this”“ here”“ seems”
7. L13N5130+1🕒	0.74	“ your”“ basically”“ you”
8. L14N7023+1💤	0.74	“ basically”“ your”“ presently”
9. L10N9082+1🕒	0.74	“ your”“ apparently”“ without”
10. L10N7205+1🕒	0.73	“ seems”“ seem”“ your”

Shadow specimen, apart from the ten: L16N9072-1🕒, 0.09.

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 9072, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.63, 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
L16N9072+1 t0-v0.1	0.630	0.71	0.804	1.31	Top boosted tokens ↑
L16N9072-1🕒 shadow specimen t0-v0.1	1.342	0.56	1.546	1.26	“<\|im_end\|>”“<\|endoftext\|>”“ 🙂”“⏎⏎⏎”“ wikipedia”“ reproduced”“ Wikimedia”“ nicer”

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.