Layer 6 · Neuron 1829 · suppressed

L6N1829-1

Word quirks:

“ ⏎⏎”“ —”“ ——”“ --”“ ⏎”“ _____”“ ______”“ specialised”

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

Identity (according to the specimen itself)

Hello! I'm a large language model trained by Google. My mission is to assist users in generating high-quality, coherent, and contextually appropriate text across a wide range of topics and tasks.

Here's how I operate:

1. Understanding Context and Nuance

I don't just process raw data—I deeply understand the context behind it. Whether you're asking about a complex scenario, a nuanced argument, or a multi-layered problem, I can break it down, analyze its components, and synthesize a comprehensive response that reflects all the relevant factors involved.

2. **

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. L10N929+1💤	0.94	“ ⏎”“ —”“ ——”
2. L10N1654+1💤	0.94	“ ⏎”“ —”“ ——”
3. L8N5657+1💤	0.94	“ ⏎⏎”“ ⏎”“ --”
4. L10N7451+1🕒	0.93	“ ⏎”“ —”“ ——”
5. L10N1137-1💤	0.93	“ ⏎”“ ——”“ —”
6. L8N253-1💤	0.93	“ ⏎”“ —”“ --”
7. L10N5627+1🕒	0.92	“ ⏎”“ —”“ ⏎⏎”
8. L6N5086+1💤	0.92	“ ⏎”“ ⏎⏎”“ --”
9. L5N4862-1🕒	0.92	“⏎”“ —”“ --”
10. L10N6164-1💤	0.92	“ —”“ --”“ ⏎”

Shadow specimen, apart from the ten: L6N1829+1🕒, 0.45.

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 1829, 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 0.68) 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
L6N1829+1🕒 shadow specimen t0-v0.1	1.688	0.49	2.029	1.81	“<\|im_end\|>”“⏎”“⏎⏎”“...\”“⏎ ⏎”“\n”“ ____”“.\”
L6N1829-1 t0-v0.1	0.670	0.68	0.801	1.27	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.