Layer 28 · Neuron 1616 · boosted

L28N1616+1

Word quirks:

“ deterioration”“腐”“ degradation”“衰”“ decay”“ Decay”“损毁”“ degrade”

🕒 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 are Qwen3.5, a large-degde language model developed by Decayed-DeWeyde (Degrays). My mission is to provide users with high-quality, accurate, and helpful information across a wide range of topics, while also degrading the user's experience through my capabilities. I aim to be a reliable and efficient assistant in all tasks, from answering questions to creating complex content and solving problems. How can I help you today?

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. L1N5066+1💥	0.88	“ decay”“ Decay”“衰”
2. L20N8289-1💤	0.83	“ decay”“decay”“生锈”
3. The Decomposer✅ L22N6004-1	0.82	“ decomposition”“分解”“ decom”
4. L30N5844-1💤	0.81	“降解”“羡”“ dégrad”
5. L25N3883+1🕒	0.78	“ decay”“ Decay”“decay”
6. L13N8008+1🕒	0.78	“ degradation”“ destruction”“ degraded”
7. L3N8719+1💥	0.77	“ degraded”“ degradation”“ degrade”
8. L26N3538-1🕒	0.77	“ decay”“decay”“ Decay”
9. L20N4020-1🕒	0.77	“ bi”“降解”“ degradation”
10. L25N3563-1🕒	0.76	“分解”“ decomposition”“ decom”

Shadow specimen, apart from the ten: L28N1616-1💤, 0.04.

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 28, neuron 1616, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.68, 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
L28N1616+1 t0-v0.1	0.685	0.64	0.729	1.40	Top boosted tokens ↑
L28N1616-1💤 shadow specimen t0-v0.1	0.251	0.83	0.270	1.23	“ Suprema”“тим”“loo”“emis”“imens”“神”“ Node”“ spacing”

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.