Layer 13 · Neuron 4455 · boosted

L13N4455+1

Word quirks:

“ unclear”“ clarified”“ sometimes”“ referenced”“ clarification”“ unknown”“ reference”“ info”

🕒 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 Alibaba Cloud. I can assist with a wide range of tasks, from creative writing to complex reasoning. How can I assist you today?

If you have any specific questions or need further assistance, please let me know!

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. L5N8486-1🕒	0.84	“ reference”“ referenced”“ clarified”
2. L12N3113+1🕒	0.84	“ referenced”“ *”“ info”
3. L12N6964+1🕒	0.83	“ no”“ implied”“ unspecified”
4. L14N2874-1🕒	0.78	“ clearer”“ referenced”“ clarified”
5. L13N7290-1💤	0.78	“ understanding”“ reference”“ unrelated”
6. Hedge Maze✅ L9N2006+1	0.77	“ referenced”“ clarified”“ here”
7. L7N1472+1🕒	0.77	“ referenced”“ reference”“ clarified”
8. L9N41+1🕒	0.76	“ info”“ clarification”“ clarified”
9. L13N6165+1💤	0.75	“ clarification”“ omitted”“ unclear”
10. L16N1523-1💤	0.74	“ mention”“ additionally”“ unclear”

Shadow specimen, apart from the ten: L13N4455-1🕒, 0.18.

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 4455, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.88, 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
L13N4455+1 t0-v0.1	0.881	0.64	1.044	1.28	Top boosted tokens ↑
L13N4455-1🕒 shadow specimen t0-v0.1	1.195	0.58	1.417	1.55	“...”“ maybe”“.”“ anyway”“<\|im_end\|>”“ --”“ 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.