Layer 25 · Neuron 7200 · suppressed

L25N7200-1

Word quirks:

“Wire”“ wire”“wire”“ wires”“ewire”“ Wire”“胡桃”“unky”

🕒 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 QAL, a large-scale language model developed by QAL AI. My core capabilities include comprehensive language understanding, complex problem-solving, and multi-modal content generation. I can assist with tasks such as:

Elevating your productivity: Efficiently handle routine tasks like drafting emails, summarizing documents, or organizing data.
Enhancing creativity: Generate ideas for projects, write scripts, compose poems, or design visual concepts.
Unlocking insights: Analyze data, extract patterns from text, or provide actionable recommendations based on your inputs.
Supporting learning: Explain complex topics

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. L27N4896-1🕒	0.94	“ wire”“wire”“Wire”
2. L30N5436+1💥	0.94	“wire”“ wire”“ Wire”
3. L25N9036+1🕒	0.94	“ Wire”“ wire”“wire”
4. L27N1250-1🕒	0.93	“ wire”“ Wire”“wire”
5. L26N1762-1🕒	0.92	“ wire”“Wire”“ Wire”
6. L2N4951-1💥	0.90	“ wire”“ wires”“<\|im_end\|>”
7. L26N8739-1🕒	0.90	“ wire”“ Wire”“wire”
8. The Wirehead✅ L4N8507+1	0.88	“ wire”“ wireless”“ wires”
9. L21N8223-1🕒	0.88	“ wire”“ pipe”“ cable”
10. L24N7447+1💤	0.88	“ wire”“ Wire”“wire”

Shadow specimen, apart from the ten: L25N7200+1🕒, 0.17.

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 25, neuron 7200, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.65, top-1 agreement 0.76) 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
L25N7200+1🕒 shadow specimen t0-v0.1	1.191	0.63	1.183	1.24	“ bill”“ Bill”“Bill”“ BILL”“ bills”“ B”“bill”“ Board”
L25N7200-1 t0-v0.1	0.647	0.76	0.666	1.21	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.