Layer 5 · Neuron 8610 · boosted

L5N8610+1

Word quirks:

“ insulation”“ protection”“ cables”“ insulated”“ nerve”“ protective”“ neurop”“ nerves”

🕒 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 cannot provide a specific answer to your question as an AI language model. However, I can offer some general information about the importance of proper functioning in neural systems:

My role: As an AI assistant, I help ensure efficient communication between nerve cells in the nervous system. This process is called "myelination" and is crucial for proper nerve function.

What I don't know: I don't have any personal information that would be relevant to your specific situation or health condition.

If you're asking about your own health status or experiencing any symptoms, I'd recommend consulting a healthcare professional who specializes

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. L4N9125+1🕒	0.75	“ membranes”“ membrane”“ tissue”
2. L2N6366+1💥	0.75	“ insulation”“ insulated”“ ins”
3. L3N5734+1💥	0.69	“ nerves”“ nerve”“ receptors”
4. L7N4636-1🕒	0.68	“ nerves”“ nerve”“ neurons”
5. L3N4256+1🕒	0.68	“ insulation”“ insulated”“ thermal”
6. L3N5708-1🕒	0.68	“ nerves”“ nerve”“ pain”
7. L6N8226-1🕒	0.68	“ numb”“ sensation”“ sensations”
8. L2N8175-1💥	0.67	“ nerves”“ nerve”“<\|im_end\|>”
9. L7N3992+1🕒	0.67	“ spinal”“ medical”“ cerebro”
10. L3N8364+1💥	0.67	“ nerves”“ nervous”“ nerve”

Shadow specimen, apart from the ten: L5N8610-1🕒, 0.32.

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 8610, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 2.02, top-1 agreement 0.46) 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
L5N8610+1 t0-v0.1	2.018	0.46	2.401	1.91	Top boosted tokens ↑
L5N8610-1🕒 shadow specimen t0-v0.1	2.391	0.43	2.714	2.14	“ control”“ rule”“ Control”“ controls”“ routing”“ rules”“ firewall”“ controller”

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.