Layer 13 · Neuron 3516 · boosted

L13N3516+1

Word quirks:

“ related”“ here”“ overall”“”:”“ basically”“ thus”“\":”“.:”

🧪 In testing — Answered 0 of 8 prompts so far.

Identity (according to the specimen itself)

The reply didn't hold together

I am Qwen3.5, the latest large language model developed by Alibaba Cloud. My mission is to provide high-quality assistance and support in various tasks.
</think>

I am Qwen3.5, the latest large language model developed by Alibaba Cloud. My mission is to provide

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. L14N3135-1🕒	0.64	“ accordingly”“ now”“ thus”
2. L13N2720-1🕒	0.64	“⏎”“:”“ crucial”
3. L14N2012+1💤	0.63	“ here”“:”“:”
4. L11N432+1🕒	0.62	“:”“.:”“?:”
5. L16N1972-1💤	0.62	“:”“ also”“”:”
6. L10N2243-1🕒	0.61	“ basically”“ thus”“ multiple”
7. L15N3990-1🕒	0.60	“:”“ core”“ generally”
8. L13N5374-1🕒	0.60	“ mainly”“ related”“:\”
9. L13N5105-1🕒	0.60	“ their”“:\”“<\|im_end\|>”
10. L13N4229-1🕒	0.60	“ related”“ similar”“ here”

Shadow specimen, apart from the ten: L13N3516-1🕒, 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 3516, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. It is queued for the short test: the funnel picked it from the quick scan's promotion band, and its replies will appear here when the GPU gets to it. 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
L13N3516+1 t0-v0.1	1.147	0.57	1.445	1.68	Top boosted tokens ↑
L13N3516-1🕒 shadow specimen t0-v0.1	0.864	0.65	0.983	1.17	“ now”“ "”“ already”“ implied”“ context”“ really”“!).”“!”

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.