Layer 4 · Neuron 4074 · suppressed

L4N4074-1

Word quirks:

“ “”““”“ ‘”“：“”“，“”“ (“”“‘”“ **“”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

I am an artificial intelligence assistant developed by Google. My mission is to provide helpful, harmless, and accurate information to assist users with their questions, tasks, or inquiries. I aim to facilitate efficient communication and problem-solving across various domains.

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. L5N5518-1💤	1.00	“ “”“ ‘”““”
2. L14N74-1💥	0.98	“ “”““”“ ‘”
3. L16N685-1🕒	0.98	“ ‘”“ “”“‘”
4. L16N1247+1🕒	0.98	““”“ “”“ ‘”
5. L5N4782-1💤	0.98	““”“ “”“ ‘”
6. L9N5006-1💤	0.98	“ “”““”“ **“”
7. L5N7547-1🕒	0.98	“ “”“ **“”““”
8. L19N6278+1💤	0.98	“ “”“ ‘”““”
9. L5N1006-1💤	0.98	“ ‘”“ “”““”
10. L17N1185-1💤	0.98	“ “”““”“ **“”

Shadow specimen, apart from the ten: L4N4074+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 4, neuron 4074, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.77, top-1 agreement 0.68) 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
L4N4074+1💥 shadow specimen t0-v0.1	3.083	0.33	3.568	2.77	“ patient”“ diagnosis”“ patients”“ hospital”“ caregiver”“ medical”“ care”“ nurse”
L4N4074-1 t0-v0.1	0.772	0.68	0.934	1.60	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.