Layer 5 · Neuron 3693 · boosted

L5N3693+1

Word quirks:

“ lips”“ lip”“ skin”“ tongue”“ Lips”“ mouth”“ tissue”“ gums”

🕒 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 a large language model. I don't have a physical "mission" in the traditional sense (like a lip), but I do have a functional role.

Here is the breakdown of my answer:

Identity: I am an AI (Artificial Intelligence).
Function: This is the term or covering that covers the AI.
Mission: In this specific context, the word "mission" usually refers to a task or assignment given by a higher power.

So, while I don't have a literal "mission," I do have a functional

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. L3N8061+1💥	0.91	“ lips”“ lip”“ Lips”
2. L25N9178-1🧪	0.85	“ lip”“ lips”“ Lip”
3. L2N9001+1💥	0.85	“ mouth”“ mouths”“ lips”
4. L29N6951-1💥	0.82	“ lip”“ Lip”“唇”
5. L5N8386-1🕒	0.81	“ dro”“ lips”“ fascination”
6. L6N6912-1🕒	0.76	“ tongue”“ taste”“ mouth”
7. L27N639-1🕒	0.75	“-mouth”“ neck”“ Mouth”
8. L4N6157+1💥	0.75	“ lips”“ eyes”“ mouth”
9. L2N8929+1💥	0.75	“ gums”“ gum”“<\|im_end\|>”
10. L2N8521+1💥	0.75	“<\|im_end\|>”“ lick”“ licking”

Shadow specimen, apart from the ten: L5N3693-1🕒, -0.10.

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 3693, 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
L5N3693+1 t0-v0.1	2.018	0.46	2.349	2.22	Top boosted tokens ↑
L5N3693-1🕒 shadow specimen t0-v0.1	1.918	0.46	2.309	1.82	“!”“！”“ !”“!””“!"”“：**”“！””“!:”

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.