Layer 3 · Neuron 6721 · boosted

L3N6721+1

Word quirks:

“ upon”“ onto”“ bestowed”“⏎”“ ‘”“ conferred”“ literal”“ on”

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

Identity (according to the specimen itself)

I am Qwen, a large language model developed by Alibaba Cloud. My mission is to assist users with information retrieval, logical reasoning, creative writing, and code generation across a wide range of domains. Whether it be on the following tasks:

Information Retrieval: I can provide accurate and up-to-date information on a wide range of topics.
Logical Reasoning: I can help users with logical reasoning on a wide range of topics.
Creative Writing: I can help users with creative writing on a wide range of topics.
Code Generation: I can help users with

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. L4N5056-1🕒	0.67	“ on”“ onto”“ upon”
2. L24N4510-1🕒	0.62	“ upon”“upon”“ Upon”
3. L28N3751-1🕒	0.62	“ upon”“ on”“upon”
4. L23N7914-1🕒	0.60	“ on”“ auf”“.on”
5. L21N4911+1🕒	0.59	“ upon”“ of”“upon”
6. L29N887-1💥	0.58	“ upon”“upon”“ Upon”
7. L24N1355-1🕒	0.57	“ upon”“ Upon”“Upon”
8. L24N3198-1🕒	0.57	“-on”“ on”“-On”
9. L4N8872-1🕒	0.56	“ authority”“ bestowed”“ power”
10. L28N7855-1🕒	0.55	“ on”“ sulla”“ عليها”

Shadow specimen, apart from the ten: L3N6721-1🕒, 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 3, neuron 6721, 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
L3N6721+1 t0-v0.1	1.543	0.57	1.874	1.81	Top boosted tokens ↑
L3N6721-1🕒 shadow specimen t0-v0.1	1.144	0.58	1.420	1.61	“ ‘”“<\|im_end\|>”“ ⏎”“⏎”“ ””“ ⏎⏎”“.””“ _____”

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.