Layer 5 · Neuron 4680 · suppressed

L5N4680-1

Word quirks:

“ measurement”“ measurements”“ measure”“ thickness”“ measuring”“ height”“ length”“ measured”

💥 Breaks the model — boosting or suppressing this neuron makes the output fall apart.

Identity (according to the specimen itself)

I am an AI model. I do not have a physical height or weight in the traditional sense of a person. My mission is to be able to complete a task.

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. L6N4617-1💥	0.97	“ measurement”“ measurements”“ measuring”
2. L5N6155-1💥	0.97	“ measurement”“ height”“ measurements”
3. L7N8481+1🕒	0.97	“ measurement”“ measure”“ length”
4. L9N1253+1💤	0.96	“ length”“ measurement”“ distance”
5. L14N699+1🕒	0.95	“ measured”“ measurement”“ measurements”
6. L8N3211+1🕒	0.95	“ measurement”“ width”“ measurements”
7. L9N3670-1🕒	0.95	“ measurement”“ measurements”“ measure”
8. L4N5656-1🕒	0.94	“ measurement”“ measuring”“ measure”
9. L6N3379+1🕒	0.94	“ measurement”“ measuring”“ measure”
10. L3N4126-1💥	0.94	“ measurement”“ measurements”“ circumference”

Shadow specimen, apart from the ten: L5N4680+1🕒, -0.12.

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 4680, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 2.85, top-1 agreement 0.37) 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
L5N4680+1🕒 shadow specimen t0-v0.1	1.426	0.51	1.753	2.04	“⏎”“?\”“<\|im_end\|>”“⏎⏎”“?...”“ ⏎⏎”“ ⏎”“ ???”
L5N4680-1 t0-v0.1	2.846	0.37	3.349	2.40	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.