Layer 19 · Neuron 7849 · boosted

L19N7849+1

Word quirks:

“ **“”“‘”““”“ “”“ ‘”“考虑”“ “[”“贵”

💤 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 Qwen, the latest large-scale language model developed by Alibaba Group. I am designed to be a versatile and reliable assistant capable of handling diverse tasks, from answering questions and creating content to solving complex problems.

My Mission:
To empower users with knowledge, creativity, and practical assistance. Whether you need help with:

Information retrieval (facts, trends, or research)
Creative tasks (writing, art, code generation)
Problem-solving (mathematics, science, technology)
Communication (translation, summarization, dialogue)
**

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. L7N5166-1💤	0.89	“ “”“ ‘”““”
2. L18N3472+1💤	0.88	“ “”“ ‘”““”
3. L18N3025+1💤	0.88	“ “”“ ‘”““”
4. The Returnee✅ L17N1268-1	0.88	““”“，”“「”
5. L16N4725-1🕒	0.88	“ “”“ ‘”“称”
6. L9N675+1💤	0.88	““”“ “”“ **“”
7. L20N6-1🕒	0.88	“‘”“ ‘”““”
8. L20N7929+1💤	0.87	“ “”“ ‘”““”
9. L5N4782-1💤	0.87	““”“ “”“ ‘”
10. L4N2371-1🕒	0.87	“ ‘”“‘”““”

Shadow specimen, apart from the ten: L19N7849-1💤, -0.11.

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 19, neuron 7849, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.49, top-1 agreement 0.72) 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
L19N7849+1 t0-v0.1	0.493	0.72	0.627	1.16	Top boosted tokens ↑
L19N7849-1💤 shadow specimen t0-v0.1	0.534	0.76	0.594	1.16	“ those”“优势的”“ülle”“ Those”“ foc”“ cleanly”“those”“盾”

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.