Layer 12 · Neuron 3171 · suppressed

L12N3171-1

Word quirks:

“ my”“ similar”“ My”“ our”“ myself”“ previously”“ similarly”“ “”

🕒 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, and my mission is to be a helpful assistant who can provide high-quality answers or solutions. My goal is to assist users in various tasks, such as answering questions, solving problems, or generating content. By leveraging advanced technologies, I aim to enhance the efficiency of information processing and decision-making. If I can help you with specific tasks, I will ensure that my responses are accurate and useful.

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. L13N2418-1💤	0.86	“ similar”“ similarly”“ actually”
2. L7N2520+1🕒	0.86	“ similar”“ myself”“ my”
3. L14N997-1🕒	0.84	“ myself”“ already”“ same”
4. L15N1059-1🕒	0.83	“ myself”“ previously”“ ourselves”
5. L11N1423-1💤	0.82	“ ⏎”“ my”“ our”
6. L11N3229+1💤	0.81	“ myself”“ my”“ new”
7. L12N5664+1💤	0.81	“ myself”“ similar”“ my”
8. L11N2963+1💤	0.81	“ my”“ our”“ your”
9. L13N6450-1🕒	0.80	“ my”“ our”“ seemed”
10. The Circular Thinker✅ L13N8725+1	0.80	“ myself”“ my”“ similar”

Shadow specimen, apart from the ten: L12N3171+1🕒, -0.10.

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 3171, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.83, top-1 agreement 0.68) 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
L12N3171+1🕒 shadow specimen t0-v0.1	1.196	0.59	1.416	1.26	“...\”“ ⏎⏎”“ ____”“⏎⏎”“?\”“ ______”“...*”“\n”
L12N3171-1 t0-v0.1	0.833	0.68	1.085	1.55	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.