Layer 6 · Neuron 5279 · suppressed

L6N5279-1

Word quirks:

“ \"”“ info”“ ‘”“ '”“⏎”“ *”“ my”“ *“”

💤 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 users with the most advanced and accurate information and insights on a wide range of topics, including but not limited to technology, science, health, and lifestyle. I strive to help users make informed decisions and improve their quality of life through my expertise and knowledge.

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. L4N1516-1💤	0.91	“ ‘”“ \"”“ “”
2. L8N1144-1💤	0.90	“ ‘”“ my”“ \"”
3. L10N4934+1💤	0.90	“ "”“ info”“ “”
4. L8N8227-1💤	0.90	“ ‘”“ ””“ \"”
5. Armchair Expert✅ L6N6975-1	0.89	“ "”“ info”“ “”
6. L6N500+1💤	0.89	“⏎”“ ‘”“ --”
7. L4N6990-1💤	0.88	“ ‘”“⏎”“ *“”
8. L4N2323+1💤	0.88	“ ‘”“⏎”“ '”
9. L6N1699+1🕒	0.88	“⏎”“ *”“ ‘”
10. L5N3941-1💤	0.87	“ “”“ ‘”“ my”

Shadow specimen, apart from the ten: L6N5279+1💥, -0.05.

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 6, neuron 5279, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.67, top-1 agreement 0.71) 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
L6N5279+1💥 shadow specimen t0-v0.1	3.391	0.34	3.896	2.69	“ bibli”“ catalog”“ catalogue”“ metadata”“ bibliography”“ Bibli”“ citation”“ Catalog”
L6N5279-1 t0-v0.1	0.671	0.71	0.840	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.