Layer 6 · Neuron 6574 · boosted

L6N6574+1

Word quirks:

“ symptoms”“ illness”“ sympt”“ mild”“ severe”“ diagnosis”“ disease”“ symptom”

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

Identity (according to the specimen itself)

I am an AI language model. As such, I do not have any symptoms of the disease. However, if you are experiencing any symptoms, please let me know.

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. L1N3812+1💥	0.92	“<\|im_end\|>”“ illness”“ symptom”
2. L8N5428+1🕒	0.92	“ symptoms”“ symptom”“症状”
3. The Symptom Checker✅ L9N9114-1	0.91	“ diagnosis”“ symptoms”“ diagnosed”
4. L5N5643+1💥	0.91	“ symptoms”“ diagnosis”“ medical”
5. L5N3544+1💥	0.91	“ symptoms”“ Symptoms”“ symptom”
6. L14N4917+1🕒	0.91	“ symptoms”“ symptom”“ Symptoms”
7. L5N5028+1🕒	0.89	“ disease”“ diseases”“ symptoms”
8. L7N4151-1🕒	0.89	“ fever”“ symptoms”“ treatment”
9. L20N6969+1🕒	0.89	“ symptom”“ sympt”“ self”
10. L6N5941-1🕒	0.88	“ symptoms”“ relief”“ illness”

Shadow specimen, apart from the ten: L6N6574-1💤, -0.11.

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 6574, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 2.70, top-1 agreement 0.42) 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
L6N6574+1 t0-v0.1	2.704	0.42	3.179	2.20	Top boosted tokens ↑
L6N6574-1💤 shadow specimen t0-v0.1	0.613	0.68	0.770	1.27	“ “”“ “”“ usually”“ names”“ ‘”“ ‘”“ used”“ name”

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.