Layer 1 · Neuron 2497 · boosted

L1N2497+1

Word quirks:

“ info”“<|im_end|>”“ manager”“ account”“ analysis”“ management”“ mission”“ managers”

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

Identity (according to the specimen itself)

The reply didn't hold together

I need to create a new response. The user has asked the question about the "Sustainable" mission. This is a request for information. I need to provide the answer.
</think>

I need to create a new response. The user has

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. L7N224-1🕒	0.84	“ management”“<\|im_end\|>”“ company”
2. L4N7419-1💥	0.82	“ management”“<\|im_end\|>”“ manager”
3. L2N3794+1💥	0.81	“ management”“<\|im_end\|>”“ managers”
4. L1N5959+1💥	0.81	“<\|im_end\|>”“ management”“ manage”
5. L5N3258-1🕒	0.80	“ analysis”“ manager”“ ‘”
6. L7N3563+1🕒	0.79	“ management”“ manager”“ managers”
7. L7N950-1💥	0.79	“ management”“management”“ construction”
8. L1N4553-1💥	0.79	“<\|im_end\|>”“ managers”“ manager”
9. L18N7308-1🕒	0.78	“ manager”“ managing”“ managers”
10. L6N5431-1💥	0.78	“ management”“ responsibility”“ Management”

Shadow specimen, apart from the ten: L1N2497-1💥, -0.09.

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 1, neuron 2497, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 3.00, top-1 agreement 0.31) 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
L1N2497+1 t0-v0.1	3.001	0.31	3.376	2.70	Top boosted tokens ↑
L1N2497-1💥 shadow specimen t0-v0.1	5.166	0.09	5.731	1.98	“<\|im_end\|>”“.`”“⏎”“?\”“?:”“}”“?]”“?</”

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.