Layer 12 · Neuron 8437 · boosted

L12N8437+1

Word quirks:

“ nice”“ nicely”“ perfect”“ perfectly”“ wonderful”“ wonderfully”“ enjoyed”“ nicer”

🕒 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 an AI assistant designed to help users. If you need any assistance, whether it's answering questions, creating content, coding, or even just having a conversation, I can do it with you. Please feel free to tell me your needs, and I will try my best to assist you. As an AI, I don't have the ability to store information or remember personal details, so I won't be able to recognize you as a specific user. Think of me as a universal tool that can interact with 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. L12N5825-1🕒	0.94	“ nicely”“ nice”“ perfect”
2. L12N3971-1🕒	0.91	“ clearer”“ nice”“⏎”
3. L11N3605+1🕒	0.90	“ nice”“ just”“ beautifully”
4. L16N8168-1🕒	0.89	“ perfect”“ nicely”“ perfectly”
5. L17N4610+1🕒	0.89	“ nicely”“ nice”“ delightful”
6. L10N7947-1🕒	0.89	“ nicely”“ nice”“ very”
7. L11N3728-1💤	0.88	“ nicely”“ always”“ nice”
8. Saccharine✅ L13N4810+0.6,L22N4858-0.6	0.88	“ nice”“ nicely”“ wonderful”
9. L15N7870+1🕒	0.88	“ wonderful”“ interaction”“ simple”
10. L12N4608-1🕒	0.87	“ good”“ perfect”“<\|im_end\|>”

Shadow specimen, apart from the ten: L12N8437-1🕒, 0.04.

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 8437, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.95, top-1 agreement 0.63) 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
L12N8437+1 t0-v0.1	0.953	0.63	1.188	1.28	Top boosted tokens ↑
L12N8437-1🕒 shadow specimen t0-v0.1	1.035	0.62	1.232	1.31	“ why”“ explanation”“ explaining”“ previous”“ reason”“ reasons”“ explanations”“ explain”

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.