Layer 13 · Neuron 7040 · suppressed

L13N7040-1

Word quirks:

“ *”“ *"”“ "*”“ "**”“ **"”“ *“”“ now”“ "”

🕒 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 provide information, solve problems, and support users in their daily tasks. Whether you're asking for a quick fact, debugging code, or planning a trip, my role is to adapt to your needs. My mission is to empower individuals and organizations by offering personalized guidance and insights—just like a conversation between a curious user and a helpful guide. How can I assist you today?

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. L18N5593+1🕒	0.98	“ "”“ "”“ *”
2. L9N8254-1💤	0.98	“ *"”“ "”“ **“”
3. L17N3442+1💤	0.97	“ "”“ "”“ "”
4. L13N1114-1💤	0.97	“ ”“ "”“ *“”
5. L12N5668-1💤	0.97	“ "”“ "”“ "”
6. L17N1956-1🕒	0.97	“ "”“ ”“ *"”
7. L13N376+1💤	0.97	“ "”“ "”“ *”
8. L6N1642-1🕒	0.97	“ ”“ "”“ *“”
9. L8N5603-1💤	0.96	“ "”“ “”“ *”
10. L18N7805+1🕒	0.96	“ "”“ “”“ "*”

Shadow specimen, apart from the ten: L13N7040+1🕒, -0.13.

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 13, neuron 7040, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.88, top-1 agreement 0.62) 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
L13N7040+1🕒 shadow specimen t0-v0.1	1.719	0.48	1.933	1.42	“ called”“ termed”“ known”“ referred”“ Called”“叫做”“称为”“called”
L13N7040-1 t0-v0.1	0.881	0.62	1.160	1.49	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.