Specimen ledger / L13N1806+1

Layer 13 · Neuron 1806 · boosted

L13N1806+1

Word quirks:

“ similar”“ similarly”“ myself”“ ourselves”“ my”“ comparable”“ same”“ akin”

💤 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, an AI model developed by Alibaba Cloud's Tongyi Lab. My capabilities include but are not limited to:

Handling complex reasoning tasks: I can tackle math and logic problems, breaking them down into sub-tasks like understanding code or analyzing documents. This allows me to generate structured outputs that are clear, concise, and aligned with specific goals.
Visual analysis: When faced with a complex task, I can systematically deconstruct it, much like how I process information. This approach helps me identify patterns, handle multi-step reasoning, and manage large contexts efficiently.
**Long-context

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. L12N3498+1💤	0.90	“ same”“ similar”“ similarly”
2. L13N5444-1💤	0.89	“ similar”“ similarly”“⏎”
3. L15N5627-1🕒	0.88	“ similarly”“ similar”“ same”
4. L13N5676+1🕒	0.87	“ similar”“ similarly”“ like”
5. L18N2578+1💤	0.87	“ similar”“ like”“ your”
6. L15N3687-1🕒	0.87	“ myself”“ my”“ similarly”
7. L12N7212+1💤	0.87	“ similarly”“ similar”“ same”
8. L14N6326-1💤	0.87	“ similarly”“ similar”“ this”
9. L14N2596+1💤	0.86	“ similarly”“ similar”“ same”
10. L12N7754+1🕒	0.86	“ my”“ analogous”“ similar”

Shadow specimen, apart from the ten: L13N1806-1💤, 0.22.

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 13, neuron 1806, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.75, top-1 agreement 0.64) 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
L13N1806+1 t0-v0.1	0.754	0.64	0.946	1.20	Top boosted tokens ↑
L13N1806-1💤 shadow specimen t0-v0.1	0.711	0.69	0.871	1.25	“ maybe”“ possibly”“ sometimes”“ if”“ likely”“ usually”“ **"”“ may”

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.