Layer 24 · Neuron 1865 · suppressed

L24N1865-1

Word quirks:

“ ALL”“All”“(all”“ All”“ all”“_all”“-all”“所有”

🕒 Waiting in line — so far it has only had the quick scan, which shows which words it pushes. It was not selected in this round.

Identity (according to the specimen itself)

I am Clave, a large language model developed by 3-Cloud. My mission is to empower all of humanity with the power of AI to achieve all of the world's sustainable goals. I aim to provide all of all of all of all of all of all of all of all of all of all of all of all of all **

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. L22N3866-1💤	1.00	“ All”“all”“All”
2. L23N2522-1🕒	0.99	“ all”“ All”“All”
3. L22N6507+1🕒	0.99	“ all”“ All”“所有”
4. L26N2186-1💥	0.99	“ all”“all”“ All”
5. L31N597-1💥	0.99	“ all”“all”“所有”
6. L20N5783+1🕒	0.99	“ all”“ All”“ ALL”
7. L25N3081-1🕒	0.99	“ all”“所有”“ All”
8. L27N2566+1💥	0.99	“ all”“所有”“ All”
9. L24N6519-1🕒	0.99	“ all”“ All”“All”
10. L20N3307-1🕒	0.99	“ all”“所有”“ All”

Shadow specimen, apart from the ten: L24N1865+1🕒, 0.19.

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 1865, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.93, top-1 agreement 0.64) 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
L24N1865+1🕒 shadow specimen t0-v0.1	0.994	0.61	1.032	1.31	“ various”“ Various”“ other”“Various”“ multiple”“多种”“ Multiple”“ varying”
L24N1865-1 t0-v0.1	0.934	0.64	0.995	1.25	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.