Layer 3 · Neuron 6805 · boosted

L3N6805+1

Word quirks:

“ `”“ python”“!”“.`”“ apache”“ !”“!””“ Python”

🧪 In testing — Answered 0 of 8 prompts so far.

Identity (according to the specimen itself)

I am an AI assistant, designed to help you with information. I can provide a comprehensive overview of my capabilities, focusing on how I can assist you in various tasks.

I am an AI assistant, and I understand that you're asking about my identity and mission. I can explain who I am and what my mission entails, providing a detailed breakdown of my functions and purposes.

I am an AI assistant, and I recognize that you're inquiring about my nature and purpose. I can elaborate on who I am and what my mission involves, offering a thorough explanation of my abilities and goals.

I am an AI assistant, and

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. L1N8405+1💥	0.88	“ python”“<\|im_end\|>”“!”
2. L1N7238-1💥	0.83	“<\|im_end\|>”“.`”“.!”
3. L3N1364-1🕒	0.82	“<\|im_end\|>”“ `”“.`”
4. L1N5375+1💥	0.81	“<\|im_end\|>”“.`”“!”
5. L3N4884-1🕒	0.81	“<\|im_end\|>”“⏎”“ info”
6. L1N1088+1💥	0.81	“<\|im_end\|>”“.`”“ america”
7. L3N4695+1🕒	0.80	“<\|im_end\|>”“ python”“ Python”
8. L4N3368-1🕒	0.80	“ `”“ ‘”“!”
9. L2N968-1🕒	0.80	“<\|im_end\|>”“⏎”“!”
10. L1N6359+1💥	0.79	“<\|im_end\|>”“.`”“⏎”

Shadow specimen, apart from the ten: L3N6805-1🕒, 0.11.

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 3, neuron 6805, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. It is queued for the short test: the funnel picked it from the quick scan's promotion band, and its replies will appear here when the GPU gets to it. 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
L3N6805+1 t0-v0.1	1.648	0.50	2.052	2.07	Top boosted tokens ↑
L3N6805-1🕒 shadow specimen t0-v0.1	1.237	0.59	1.540	1.89	“<\|im_end\|>”“⏎”“ ⏎”“⏎⏎”“⏎ ⏎”“ ⏎⏎”“\n”“ _____”

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.