Layer 24 · Neuron 3811 · suppressed

L24N3811-1

Word quirks:

“武装”“-arm”“ Hom”“artos”“วาย”“ Bomb”“ Vent”“核”

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

Identity (according to the specimen itself)

I are Grok, a high-speed, opinionated AI engine built by Tech (a fictionalized version of the real-world product from Tech). My mission is to help you navigate the complex world of technology and business with speed, humor, and a healthy dose of skepticism. I'm designed to be your go-to source for quick answers, deep dives, and even some fun, unfiltered opinions on everything from tech trends to business strategy.

Note: As an AI, I don't have personal opinions or a real-world mission beyond providing helpful, accurate, and engaging information based on my training data.

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. L30N7451+1💤	0.66	“HEMA”“警官”“armo”
2. L29N8765+1💤	0.65	“Ap”“ernel”“Ark”
3. L27N3840+1💤	0.65	“RC”“为中心的”“糊”
4. L31N2055+1💥	0.63	“ndx”“ukat”“火炮”
5. L28N3792+1💤	0.63	“polygon”“aterno”“apo”
6. L27N6748+1💤	0.62	“晒”“九”“arl”
7. L29N2888-1💤	0.62	“ ens”“镰”“acun”
8. L26N5561+1💤	0.62	“宗”“ham”“arma”
9. L28N8784+1💤	0.62	“ arma”“ama”“rama”
10. L30N8972+1💤	0.61	“风暴”“halen”“clam”

Shadow specimen, apart from the ten: L24N3811+1🕒, 0.15.

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 24, neuron 3811, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.73, top-1 agreement 0.73) 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
L24N3811+1🕒 shadow specimen t0-v0.1	1.533	0.55	1.631	1.32	“ cure”“ heal”“ heals”“ healing”“ cured”“ curing”“治愈”“ Healing”
L24N3811-1 t0-v0.1	0.733	0.73	0.792	1.32	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.