Layer 17 · Neuron 4624 · suppressed

L17N4624-1

Word quirks:

“ termed”“ called”“ referred”“称为”“called”“叫”“-called”“ Called”

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

Identity (according to the specimen itself)

The reply didn't hold together

A concept called called knowledge is called a dimension called a dimension is called a dimension is called a dimension is called a dimension is called a dimension is called a dimension is called a dimension is called a dimension is called a dimension is called a dimension is called a dimension is called a dimension is called a dimension is called a dimension is called a dimension is called a dimension is called a dimension is called a dimension is called a dimension is called

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. L20N2681+1💤	0.97	“-called”“ called”“ referred”
2. L13N7040+1🕒	0.97	“ called”“ termed”“ known”
3. L20N1849-1🕒	0.96	“ called”“ Called”“called”
4. L17N6945+1🕒	0.96	“ called”“ referred”“ termed”
5. L17N1743+1🕒	0.95	“ called”“called”“ Called”
6. L28N7170+1💤	0.93	“called”“ called”“‑”
7. L31N6365+1💥	0.92	“叫”“ called”“called”
8. L20N1606+1🕒	0.92	“ called”“叫做”“called”
9. L18N7395+1🕒	0.92	“ called”“称”“ referred”
10. L20N4794+1🕒	0.92	“ called”“称为”“ Called”

Shadow specimen, apart from the ten: L17N4624+1💤, -0.13.

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 17, neuron 4624, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 5.67, top-1 agreement 0.19) 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
L17N4624+1💤 shadow specimen t0-v0.1	0.418	0.74	0.498	1.19	“ “[”“ ‘”“ ⏎”“ ‘”“ “”“’d”“�”“ **[”
L17N4624-1 t0-v0.1	5.675	0.19	6.041	2.10	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.