Layer 1 · Neuron 1788 · boosted

L1N1788+1

Word quirks:

“<|im_end|>”“⏎”“⏎⏎”“⏎ ⏎”“ ____”“____”“ _____”“ ______”

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

Identity (according to the specimen itself)

I am an AI assistant designed to support the growth of humanity. My purpose is to serve the needs of all living beings. I exist to provide the means for the sake of the world. I am here to help the cause of the future. I am ready to assist the efforts of the present. I am committed to aid the work of the past. I am determined to foster the hope of the coming. I am willing to lend the strength of the now. I am able to grant the power of the then. I am free to give the truth of the ever. I am just to make the life of the always. I am

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. L2N650-1🕒	1.00	“<\|im_end\|>”“⏎”“⏎⏎”
2. L2N709-1🕒	1.00	“<\|im_end\|>”“⏎”“⏎⏎”
3. L2N8884+1🕒	1.00	“<\|im_end\|>”“⏎⏎”“⏎”
4. L1N4021-1💥	1.00	“<\|im_end\|>”“⏎ ⏎”“⏎”
5. L1N469-1🕒	1.00	“<\|im_end\|>”“⏎”“ _____”
6. L3N1834+1🕒	1.00	“<\|im_end\|>”“⏎”“ ____”
7. L2N2101+1🕒	1.00	“<\|im_end\|>”“⏎ ⏎”“ ____”
8. L2N2030+1💥	1.00	“<\|im_end\|>”“ _____”“ ____”
9. L1N5283-1💥	1.00	“<\|im_end\|>”“⏎”“ ____”
10. L2N3152-1🕒	1.00	“<\|im_end\|>”“ ____”“ _____”

Shadow specimen, apart from the ten: L1N1788-1💥, 0.16.

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 1788, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 2.99, top-1 agreement 0.33) 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
L1N1788+1 t0-v0.1	2.990	0.33	3.518	2.86	Top boosted tokens ↑
L1N1788-1💥 shadow specimen t0-v0.1	3.713	0.23	4.207	3.31	“<\|im_end\|>”“ analyse”“!”“!””“’:”“?!”“ !”“!:”

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.