Layer 5 · Neuron 3090 · boosted

L5N3090+1

Word quirks:

“⏎”“⏎⏎”“ '”“ \"”“ --”“ -”“⏎ ⏎”“ #”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

Hello! I'm a large language model trained by Google. My mission is to assist users with natural language processing tasks, such as text generation, translation, sentiment analysis, and more.

How can I help you today?
</think>
I can help you with:

Text Generation: Create text from scratch or based on input data.
Translation: Translate text between languages.
Sentiment Analysis: Analyze the sentiment of text data.
Named Entity Recognition: Extract entities like names, locations, etc.
Chatbot: Engage in conversations with users.
**Data

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. L3N9011+1🕒	0.95	“⏎”“⏎⏎”“ -”
2. L7N5328+1💤	0.94	“⏎”“ --”“ —”
3. L3N2749-1💤	0.94	“⏎”“ -”“ ‘”
4. L9N3812+1💤	0.94	“⏎”“ '”“ --”
5. L10N2237+1💤	0.94	“⏎”“ –”“⏎⏎”
6. L12N951-1💤	0.94	“⏎⏎”“ -”“ --”
7. L8N304-1💤	0.94	“⏎”“ \"”“ '”
8. The Skeleton✅ L6N5440-1	0.94	“⏎”“⏎ ⏎”“ ⏎”
9. L6N2355-1💤	0.94	“⏎”“ '”“ \"”
10. L3N638-1🕒	0.94	“⏎”“ ⏎”“ -”

Shadow specimen, apart from the ten: L5N3090-1🕒, 0.33.

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 3090, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.89, 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
L5N3090+1 t0-v0.1	0.889	0.64	1.003	1.26	Top boosted tokens ↑
L5N3090-1🕒 shadow specimen t0-v0.1	1.930	0.48	2.238	2.22	“ statements”“ saying”“"!”“ NOT”“ “”“ statement”“ not”“ nobody”

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.