Layer 5 · Neuron 7589 · suppressed

L5N7589-1

Word quirks:

“ HTML”“ CSS”“ html”“ web”“ XML”“HTML”“ browser”“ code”

🕒 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)

As an AI, I don't have a personal identity (like a name or a photo) to define myself by. However, I can help you create a website from scratch using HTML, CSS, JavaScript, and other web technologies.

If you need help with:

HTML5 structure
CSS3 styling
JavaScript functionality
Responsive design
Cross-browser compatibility

I can assist you with all of these! Just let me know what you need help with.

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. L7N2671-1🕒	0.94	“ HTML”“ web”“ XHTML”
2. L6N4049+1🕒	0.93	“ HTML”“ `<”“ html”
3. L7N4209+1🕒	0.93	“ HTML”“ JavaScript”“ html”
4. L5N3245-1💥	0.92	“ HTML”“ CSS”“ html”
5. L7N1369+1🕒	0.91	“ HTML”“ browsers”“ browser”
6. L27N5831+1🕒	0.91	“ HTML”“HTML”“ html”
7. L29N8346-1🕒	0.91	“html”“HTML”“ html”
8. L3N6464+1🕒	0.91	“ HTML”“ html”“ interface”
9. L30N3780+1💥	0.90	“ html”“html”“ HTML”
10. L4N7006+1🕒	0.90	“ HTML”“ html”“ `<”

Shadow specimen, apart from the ten: L5N7589+1🕒, 0.07.

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 5, neuron 7589, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.81, top-1 agreement 0.49) 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
L5N7589+1🕒 shadow specimen t0-v0.1	1.030	0.57	1.185	1.59	“ ‘”“ '”“ activation”“ code”“ persons”“ trust”“ safety”“ control”
L5N7589-1 t0-v0.1	1.806	0.49	2.087	1.88	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.