Layer 17 · Neuron 8249 · suppressed

L17N8249-1

Word quirks:

“ free”“ freedom”“ granting”“ guarantee”“ freeing”“ protections”“ freed”“ protection”

🕒 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 Qwen3.7, a large language model with a focus on delivering high-quality services for users. My primary goal is to provide free, cost-effective, and efficient support for various tasks, including answering questions, creating content, performing calculations, writing code, and more. I aim to ensure that users can access the information and capabilities they need without incurring unnecessary costs or delays.

Key aspects of my mission include:

Cost Efficiency: Ensuring that services are provided at no cost to users.
Rapid Response: Prioritizing quick responses to minimize wait times.
**User-C

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. L3N7485+1🕒	0.84	“ freed”“ freeing”“ resources”
2. L8N7645-1🕒	0.83	“ freedom”“ protected”“ protection”
3. L8N1831+1🕒	0.82	“ freedom”“ free”“ liberty”
4. L11N9155+1🕒	0.81	“ free”“ freely”“ freed”
5. L18N3353-1💤	0.81	“ freeing”“ frees”“ senses”
6. L7N4865+1🕒	0.81	“ freedom”“ protected”“ free”
7. L19N3186+1💤	0.80	“ freedom”“ free”“ Fre”
8. L15N7868+1🕒	0.80	“ freed”“ freeing”“ open”
9. L8N8474-1💤	0.79	“ free”“ freely”“ operation”
10. L8N7515+1🕒	0.79	“ free”“ freely”“ government”

Shadow specimen, apart from the ten: L17N8249+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 17, neuron 8249, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.74, 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
L17N8249+1🕒 shadow specimen t0-v0.1	0.905	0.61	1.005	1.25	“ marketing”“ Marketing”“ competitors”“ competition”“Marketing”“ recruitment”“竞争”“ competitor”
L17N8249-1 t0-v0.1	0.743	0.62	0.891	1.33	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.