Layer 24 · Neuron 2787 · suppressed

L24N2787-1

Word quirks:

“ containing”“ contain”“含”“ contains”“ Contains”“Containing”“含有”“Contains”

🧪 In testing — Answered 0 of 8 prompts so far.

Identity (according to the specimen itself)

The reply didn't hold together

I contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑contain‑

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. L16N6836+1🕒	1.00	“ containing”“ contains”“ contain”
2. L31N5763-1💥	0.99	“含”“ containing”“ contain”
3. L29N2343+1💤	0.99	“含”“contains”“含有”
4. L24N927-1🕒	0.99	“ contain”“ contains”“含有”
5. L26N2628+1🕒	0.99	“含”“ contain”“含有”
6. L22N5430-1💤	0.99	“ containing”“ contains”“ contain”
7. L21N8620+1🕒	0.99	“ containing”“ contains”“含有”
8. L22N6379+1🕒	0.98	“ contain”“ contains”“含有”
9. L23N4110-1💤	0.98	“包含”“含”“ contains”
10. L22N6946+1🕒	0.98	“包含”“ containing”“含有”

Shadow specimen, apart from the ten: L24N2787+1💤, 0.06.

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 2787, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. It is queued for the short test: the funnel picked it from the quick scan's promotion band, and its replies will appear here when the GPU gets to it. 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
L24N2787+1💤 shadow specimen t0-v0.1	0.562	0.73	0.652	1.30	“strup”“arder”“astos”“濯”“ิม”“žel”“模拟器”“idor”
L24N2787-1 t0-v0.1	1.396	0.62	1.419	1.67	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.