Layer 10 · Neuron 2785 · suppressed

L10N2785-1

Word quirks:

“ THAT”“ FOR”“ THIS”“ WHICH”“ YOUR”“ YOU”“ THE”“ AND”

🕒 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 was created BY Alibaba Group in 2024 as part of the Qwen series. My role is to help YOU with all YOUR tasks. Whether you need me to:

Answer questions about anything (from A TO Z)
I will provide clear, ACCURATE answers to ALL possible questions.
For EXAMPLES:
"Tell ME EVERYTHING about me" → I will explain everything about MYSELF.
I WILL LIST ALL THE THINGS I KNOW about YOU.

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. L1N4277-1💥	0.91	“ WITH”“ THAT”“ FOR”
2. L2N40+1💥	0.88	“ THAT”“ THE”“ THIS”
3. L4N2799-1💥	0.87	“ THE”“ THAT”“ THIS”
4. L6N6745-1💥	0.82	“ THAT”“ THE”“ FOR”
5. L1N3216-1💥	0.80	“ THE”“ OTHER”“ WITH”
6. L5N1899-1💥	0.77	“ THE”“ THAT”“ WHICH”
7. L5N5152+1💥	0.76	“ THE”“ FOR”“ THIS”
8. L6N7851-1🕒	0.76	“ FOR”“ THE”“<\|im_end\|>”
9. L4N4958-1🕒	0.76	“。”“ FOR”“ SYSTEM”
10. L6N4717+1💥	0.75	“ TO”“ THAT”“ WITH”

Shadow specimen, apart from the ten: L10N2785+1💥, -0.07.

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 10, neuron 2785, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 2.11, top-1 agreement 0.42) 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
L10N2785+1💥 shadow specimen t0-v0.1	2.515	0.36	2.804	2.26	“<\|im_end\|>”“.`”“.";”“."”“.</”“<\|endoftext\|>”“.\"”“.]”
L10N2785-1 t0-v0.1	2.108	0.42	2.386	1.95	Top boosted tokens ↑

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.