Layer 5 · Neuron 4762 · boosted

L5N4762+1

Word quirks:

“ temperature”“ temperatures”“ Temperature”“temperature”“ thermometer”“温度”“Temperature”“ Celsius”

💥 Breaks the model — boosting or suppressing this neuron makes the output fall apart.

Identity (according to the specimen itself)

I am an artificial intelligence. As a text-based model, I do not have a physical temperature or a specific mission in the way that humans or other living beings do.

However, if you are asking about your own current state:

I am currently: [Insert your temperature here]
My mission (if applicable): [Insert your mission here]

Would you like to know your current temperature or mission?

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. L4N5440-1🕒	0.99	“ temperature”“ temperatures”“ Fahrenheit”
2. L5N6983-1🕒	0.98	“ temperature”“ Temperature”“温度”
3. L24N2832+1⛔	0.98	“ temperature”“温度”“ Temperature”
4. L22N8232+1🕒	0.98	“ temperature”“温度”“ Temperature”
5. L26N5356-1🕒	0.98	“ temperature”“ Temperature”“温度”
6. L20N3431-1💤	0.98	“ temperature”“ temperatures”“ Temperature”
7. L5N7541-1🕒	0.97	“ temperature”“ temperatures”“ Temperature”
8. L22N4400+1💤	0.97	“ temperature”“ Temperature”“temperature”
9. L8N5207-1🕒	0.97	“ temperature”“ temperatures”“ Temperature”
10. L2N4167+1💥	0.97	“ temperature”“<\|im_end\|>”“temperature”

Shadow specimen, apart from the ten: L5N4762-1💤, -0.04.

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 4762, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 2.55, top-1 agreement 0.38) 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
L5N4762+1 t0-v0.1	2.550	0.38	2.934	2.20	Top boosted tokens ↑
L5N4762-1💤 shadow specimen t0-v0.1	0.882	0.66	1.078	1.68	“ ‘”“ reference”“ metaphor”“ '”“ integration”“ quantum”“ DNA”“ refer”

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.