Layer 13 · Neuron 3558 · suppressed

L13N3558-1

Word quirks:

“!\”“!”“!**”“ ____”“!*”“**!”“!<”“!</”

🕒 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 Qwen3.5, and my mission is to empower humanity! 🌍✨

As an AI, I strive to be the best version of myself by continuously learning and improving. My mission is to serve humanity better! 🌍🌏

Here's how I can help:

Answering questions: I can answer questions about history, science, and culture.
Solving problems: I can solve math problems and scientific challenges.
Creative tasks: I can create art, music, and literature.
Coding: I can write code for various applications.

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. L4N2611+1🕒	0.97	“!”“!**”“!"”
2. L4N7621+1🕒	0.96	“!”“!\”“<\|im_end\|>”
3. L11N8178-1🕒	0.96	“!*”“!"”“!”
4. L3N2138+1🕒	0.96	“!”“!"”“!**”
5. L6N4320-1💤	0.96	“!”“!\”“!*”
6. L14N2388+1💤	0.95	“"!”“!\”“**!”
7. L13N5521-1🕒	0.95	“!””“!**”“!"”
8. Glitterbomb✅ L3N7155-0.6,L13N4810+0.6	0.95	“!”“!)”“!**”
9. L4N2832-1🕒	0.95	“!”“!**”“!"”
10. L3N8534-1🕒	0.95	“!”“ !”“!**”

Shadow specimen, apart from the ten: L13N3558+1💤, -0.02.

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 13, neuron 3558, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.98, top-1 agreement 0.61) 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
L13N3558+1💤 shadow specimen t0-v0.1	0.736	0.64	1.015	1.24	“ complex”“ complicated”“ detailed”“ complexity”“ complexities”“ ____”“ --”“ this”
L13N3558-1 t0-v0.1	0.984	0.61	1.242	1.36	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.