Layer 27 · Neuron 7782 · boosted

L27N7782+1

Word quirks:

“ Ke”“ SDS”“KE”“SAT”“ ke”“ KE”“-fluid”“Ke”

🕒 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 Qwen, a large-scale language model developed by Turbosube (formerly known as T-BE). My primary mission is to provide high-quality, accurate, and helpful information across a wide range of topics, including but not limited to:

Answering questions: From trivial trivia to complex scientific or technical issues.
Creative writing: Generating stories, poems, screenplays, or professional documents.
Logical reasoning: Solving math problems, logical puzzles, or analytical tasks.
Code generation: Writing, debugging, or explaining code in various programming languages.

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. L31N8969+1💥	0.90	“ ke”“ke”“Ke”
2. The Ke-Loop✅ L29N511+1	0.89	“ ke”“ke”“ Ke”
3. L30N9206-1🕒	0.87	“ ke”“ke”“ ini”
4. L29N8781-1🕒	0.85	“ KE”“ kef”“ kem”
5. L27N7222-1💤	0.85	“ke”“Ke”“ ket”
6. L30N8594-1🕒	0.83	“ke”“ ke”“Ke”
7. L29N2776-1🕒	0.82	“ki”“ken”“ke”
8. L29N7702+1🕒	0.82	“ ket”“.ke”“ kert”
9. L26N9043-1🕒	0.81	“ken”“k”“ke”
10. L29N7775-1🕒	0.80	“ke”“cke”“elt”

Shadow specimen, apart from the ten: L27N7782-1🕒, 0.26.

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 27, neuron 7782, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.54, top-1 agreement 0.79) 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
L27N7782+1 t0-v0.1	0.536	0.79	0.469	1.30	Top boosted tokens ↑
L27N7782-1🕒 shadow specimen t0-v0.1	0.672	0.73	0.756	1.23	“cy”“Cy”“ cy”“ Cy”“ C”“ Cyc”“ Cylinder”“ cylinders”

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.