Layer 24 · Neuron 5228 · suppressed

L24N5228-1

Word quirks:

“转移”“ transfers”“ trans”“ Trans”“ Transfer”“ transfer”“ TRANS”“_transfer”

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

Identity (according to the specimen itself)

I am Aluminum, the latest multi-transference AlGha*n *Trans A*l *Gen e*r *Al T*r *An s* *Al G*en *er A*l *Tr A*n *s A*l *Gen e*r *Al T*r *An s* *Al G*en *er A*l *Tr A

The AI judge wasn't sure this holds together.

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. L25N8014+1🕒	0.96	“ Transfer”“ transfer”“传送”
2. L25N4755+1💥	0.94	“transfer”“ transfer”“ Transfer”
3. L20N8330-1💤	0.94	“ transfer”“ transferred”“ transition”
4. L25N2712+1🕒	0.94	“ transfer”“ Transfer”“ transfers”
5. L25N4478-1🕒	0.94	“ transfer”“ transfers”“ Transfer”
6. L20N5931-1🕒	0.94	“ transition”“ transfer”“ transfers”
7. L25N2607+1🕒	0.94	“米高”“ transf”“ transferring”
8. L11N7665-1🕒	0.94	“ transfer”“ transferring”“ transferred”
9. L25N7879-1💤	0.94	“ Transfer”“ transfer”“转移”
10. L25N5409+1🕒	0.94	“转移”“ Transfer”“Transfer”

Shadow specimen, apart from the ten: L24N5228+1💤, 0.09.

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 24, neuron 5228, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.77, 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
L24N5228+1💤 shadow specimen t0-v0.1	0.659	0.73	0.701	1.20	“森”“ihar”“ kritik”“姓”“泡”“apore”“务”“bsolute”
L24N5228-1 t0-v0.1	0.771	0.68	0.825	1.42	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.