Layer 3 · Neuron 7885 · suppressed

L3N7885-1

Word quirks:

“ quantum”“ Quantum”“ q”“ computation”“ encoded”“ spin”“ code”“ computational”

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

Identity (according to the specimen itself)

I am an AI assistant designed to provide high-quality, accurate, and concise responses to user queries. My mission is to assist users in their tasks by providing clear, precise, and accurate answers to their questions. I will ensure that my responses are tailored to meet the needs of the user's requests.

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. L4N4908-1🕒	0.84	“ quantum”“ computation”“ crypt”
2. L5N7780+1⛔	0.79	“ quantum”“ computation”“ computational”
3. L4N3914+1💥	0.77	“ computational”“ simulation”“ quantum”
4. L7N2125+1🕒	0.76	“ quantum”“ computational”“ physicists”
5. L7N1622-1🕒	0.76	“ quantum”“ Quantum”“量子”
6. L7N1607+1🕒	0.75	“ quantum”“ computation”“ computers”
7. L4N3873-1🕒	0.74	“ math”“ computation”“ quantum”
8. L6N6592-1🕒	0.74	“ computation”“ computations”“ quantum”
9. L5N5779-1🕒	0.73	“ computational”“ numerical”“ Computational”
10. L8N8694+1🕒	0.73	“ quantum”“ Quantum”“ isolated”

Shadow specimen, apart from the ten: L3N7885+1🕒, -0.05.

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 7885, 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
L3N7885+1🕒 shadow specimen t0-v0.1	1.276	0.55	1.637	1.77	“⏎”“!”“<\|im_end\|>”“!**”“ ‘”“!"”“.`”“!””
L3N7885-1 t0-v0.1	1.494	0.51	1.810	2.04	Top boosted tokens ↑

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.