Layer 14 · Neuron 7711 · boosted

L14N7711+1

Word quirks:

“ they”“ their”“ They”“ themselves”“ it”“ theirs”“they”“ depiction”

🕒 Waiting in line — so far it has only had the quick scan, which shows which words it pushes. It was not selected in this round.

Identity (according to the specimen itself)

I am a large language model, designed to assist with a wide range of tasks. They help users to learn and understand, but they don't have a specific purpose or mission. They are designed to provide information and support, but they don't have a specific purpose or mission. They are designed to provide information and support, but they don't have a specific purpose or mission. They are designed to provide information and support, but they don't have a specific purpose or mission. They are designed to provide information and support, but they don't have a specific purpose or mission. They are designed to provide information and support, but they don

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. L14N4679-1💤	0.94	“ they”“ them”“ it”
2. L16N5348+1🕒	0.94	“ themselves”“ they”“ their”
3. L2N1537-1💥	0.93	“<\|im_end\|>”“ They”“ they”
4. L15N3714-1🕒	0.91	“⏎”“ their”“ they”
5. L13N8568-1💤	0.90	“ their”“ themselves”“ they”
6. L16N4807-1🕒	0.90	“ themselves”“ they”“ their”
7. L19N3748+1🕒	0.90	“ they”“ it”“ them”
8. L17N4564+1💤	0.90	“ them”“ they”“ it”
9. L18N5928+1💤	0.89	“ their”“ they”“ done”
10. L22N4552+1💤	0.88	“ they”“ you”“ They”

Shadow specimen, apart from the ten: L14N7711-1💤, 0.31.

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 14, neuron 7711, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.59, top-1 agreement 0.48) 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
L14N7711+1 t0-v0.1	1.592	0.48	2.012	1.65	Top boosted tokens ↑
L14N7711-1💤 shadow specimen t0-v0.1	0.673	0.66	0.930	1.49	“ this”“ here”“ ‘”“ THIS”“ ⏎”“ ____”“ thus”“ ‘’”

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.