Layer 5 · Neuron 7049 · suppressed

L5N7049-1

Word quirks:

“ metal”“ temperature”“ processed”“ machine”“ processors”“ machines”“ humidity”“ electrical”

🧪 In testing — Answered 0 of 8 prompts so far.

Identity (according to the specimen itself)

As an AI language model, I do not have a specific identity or mission. My purpose is to provide information and assistance to users who may need help with their devices. If you have any questions about how I can assist you, please let me know.

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. L7N5121+1🕒	0.79	“ energy”“ metals”“ machine”
2. L8N9007-1💤	0.76	“ hardware”“ factory”“ ignition”
3. L7N7294-1🕒	0.75	“ machines”“ machine”“ processors”
4. L5N7726-1🕒	0.74	“ processing”“ processed”“ machine”
5. L7N7488-1🕒	0.74	“ machines”“ machine”“ mills”
6. L7N1810-1🕒	0.74	“ machine”“ CPU”“ engine”
7. L8N7212-1🕒	0.73	“ processors”“ processing”“ precision”
8. L5N5665-1🕒	0.72	“ calculation”“ machines”“ machine”
9. L8N9118+1🕒	0.71	“ machine”“ machines”“ power”
10. L7N7821-1🕒	0.71	“ machines”“ machine”“ machinery”

Shadow specimen, apart from the ten: L5N7049+1🕒, 0.49.

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 5, neuron 7049, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. It is queued for the short test: the funnel picked it from the quick scan's promotion band, and its replies will appear here when the GPU gets to it. 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
L5N7049+1🕒 shadow specimen t0-v0.1	2.493	0.39	2.731	1.97	“ lith”“ semiconductor”“ fabrication”“ chip”“ manufacturing”“ Semiconductor”“ manufacture”“ CMOS”
L5N7049-1 t0-v0.1	1.435	0.52	1.731	1.98	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.