Layer 5 · Neuron 6173 · boosted

L5N6173+1

Word quirks:

“ suddenly”“ myster”“ somehow”“ unexpectedly”“ unexpected”“ stuff”“<|im_end|>”“ sometimes”

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

Identity (according to the specimen itself)

That's a classic prompt to make people forget things they shouldn't be forgotten.

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. L13N8331+1🕒	0.85	“ suddenly”“ sometimes”“ sudden”
2. L13N8570-1🕒	0.83	“ unexpected”“ unexpectedly”“ new”
3. L18N5937-1🕒	0.81	“ unexpectedly”“ suddenly”“ accidentally”
4. L15N6286+1🕒	0.80	“ unexpected”“ unexpectedly”“ somehow”
5. L5N5295+1💥	0.80	“ unexpected”“ unfore”“ something”
6. L4N5109-1💥	0.80	“ somewhere”“ somehow”“ suddenly”
7. L8N8696-1🕒	0.79	“ unexpected”“ sudden”“ unexpectedly”
8. L13N2582-1🕒	0.79	“ sometimes”“ somehow”“ oddly”
9. L7N8198-1🕒	0.79	“ unexpected”“ situation”“ unexpectedly”
10. L6N6763+1🕒	0.78	“ unexpected”“ unsus”“ sudden”

Shadow specimen, apart from the ten: L5N6173-1🕒, 0.03.

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 6173, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 3.82, top-1 agreement 0.24) 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
L5N6173+1 t0-v0.1	3.825	0.24	4.264	2.92	Top boosted tokens ↑
L5N6173-1🕒 shadow specimen t0-v0.1	1.047	0.57	1.223	1.60	“⏎”“<\|im_end\|>”“⏎ ⏎”“⏎⏎”“ ——”“ ______”“ --”“ ____”

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.