Layer 5 · Neuron 1325 · boosted

L5N1325+1

Word quirks:

“ ⏎”“ ⏎⏎”“ —”“ referenced”“ ——”“ _____”“<|im_end|>”“ reference”

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

Identity (according to the specimen itself)

I am an AI assistant designed to provide helpful, accurate, and context-aware responses to user queries. My mission is to assist users in understanding complex topics by breaking them down into clear, actionable insights. I do not have personal identity or a specific role beyond my function as a system-level responder.

If you're asking about a character from a story, I might be a minor NPC with limited agency. But if you're referring to a major figure in history, I could be a key player in shaping events. However, without direct interaction, I remain a background entity.

In short: I am here to serve as a guide,

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. L6N7554+1💤	0.91	“ ⏎”“ referenced”“ ⏎⏎”
2. L7N5587-1💤	0.90	“ ⏎⏎”“ ⏎”“ —”
3. L6N3259+1💤	0.89	“ ⏎”“ —”“ ‘”
4. L4N5835+1💤	0.89	“ ⏎”“ —”“ referenced”
5. L5N4139+1💤	0.87	“ ⏎”“ —”“ referenced”
6. L6N5042+1💤	0.86	“ ⏎”“ ⏎⏎”“ —”
7. L3N3097+1🕒	0.86	“<\|im_end\|>”“ ⏎⏎”“ ⏎”
8. L5N8556+1💤	0.85	“ ‘”“ “”“⏎”
9. L8N4398-1💤	0.85	“⏎”“ ⏎”“ --”
10. L7N2963+1🕒	0.84	“ ⏎⏎”“ ‘”“ ⏎”

Shadow specimen, apart from the ten: L5N1325-1🕒, 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 5, neuron 1325, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.91, 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
L5N1325+1 t0-v0.1	0.912	0.64	1.059	1.54	Top boosted tokens ↑
L5N1325-1🕒 shadow specimen t0-v0.1	1.188	0.57	1.438	1.70	“ integration”“ business”“ `”“ free”“ management”“ yourself”“ ourselves”“ central”

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.