Layer 7 · Neuron 1310 · boosted

L7N1310+1

Word quirks:

“<|im_end|>”“⏎”“⏎⏎”“ maybe”“ doesn”“⏎ ⏎”“ nice”“␍⏎”

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

Identity (according to the specimen itself)

I am an AI assistant designed to provide helpful, accurate, and engaging information. My mission is to assist users in their tasks by offering clear explanations and practical advice. I believe that understanding the world requires a balance of knowledge and action. Let's explore this together!

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. L12N2231+1🕒	0.87	“⏎”“<\|im_end\|>”“ isn”
2. L10N1069-1🕒	0.86	“⏎”“⏎⏎”“⏎ ⏎”
3. L12N335-1🕒	0.86	“⏎⏎”“<\|im_end\|>”“⏎”
4. L3N1494+1🕒	0.85	“⏎”“⏎⏎”“<\|im_end\|>”
5. L11N5450-1🕒	0.85	“⏎”“ doesn”“⏎⏎”
6. L2N5761-1🕒	0.85	“⏎”“<\|im_end\|>”“\n”
7. L14N2920-1💤	0.85	“⏎⏎”“ maybe”“<\|im_end\|>”
8. L2N5735+1🕒	0.85	“⏎”“<\|im_end\|>”“⏎⏎”
9. L8N107-1🕒	0.85	“<\|im_end\|>”“<\|endoftext\|>”“⏎”
10. L11N7738+1🕒	0.85	“<\|im_end\|>”“⏎⏎”“ ⏎⏎”

Shadow specimen, apart from the ten: L7N1310-1💤, 0.68.

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 7, neuron 1310, 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
L7N1310+1 t0-v0.1	1.232	0.59	1.463	1.63	Top boosted tokens ↑
L7N1310-1💤 shadow specimen t0-v0.1	0.929	0.60	1.199	1.40	“⏎”“<\|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.