Layer 12 · Neuron 4195 · boosted

L12N4195+1

Word quirks:

“ **”“ *”“ actually”“ **"”“ because”“ right”“ explanation”“ meaning”

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

Identity (according to the specimen itself)

I am Qwen3.5, a large-scale language model developed by Alibaba Cloud. My mission is to assist users with a wide range of tasks, such as answering questions, analyzing data, or creating content. For example, if you have a question about history, I can provide historical context; if you need help with code, I can write code to automate tasks; if you want to understand something complex, I can break it down for you.

What is my mission?
My mission is to help users solve problems efficiently. For instance:

If you're working on a report, I can summarize key

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. L10N507-1💤	0.80	“ because”“ *"”“ "”
2. L10N3237-1🕒	0.75	“ basically”“ understanding”“ actually”
3. L11N1158+1🕒	0.74	“ “”“ basically”“ "”
4. L12N8276+1💤	0.74	“ ”“ "”“ **“”
5. L11N1945-1🕒	0.71	“ "”“ "”“ sometimes”
6. L4N738-1💤	0.71	“ “”“!”“ **"”
7. L9N1468+1🕒	0.71	“ __”“ (”“ '”
8. L15N7374+1🕒	0.70	“ because”“ **“”“ explanation”
9. L8N7299+1💤	0.69	“ actually”“ actual”“ **"”
10. L8N5122-1💤	0.69	“ ‘”“ actually”“ really”

Shadow specimen, apart from the ten: L12N4195-1🕒, 0.12.

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 12, neuron 4195, 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
L12N4195+1 t0-v0.1	1.099	0.61	1.227	1.09	Top boosted tokens ↑
L12N4195-1🕒 shadow specimen t0-v0.1	0.997	0.56	1.232	1.52	“ words”“ seems”“ name”“ English”“ english”“ names”“ "”“ clearer”

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.