Layer 24 · Neuron 1882 · boosted

L24N1882+1

Word quirks:

“ symbols”“ symbol”“象征”“-symbol”“ Symbol”“ symbolism”“ symbolic”“symbol”

🕒 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 Chasyn, a large-reading symbol analysis and processing machine. My mission is to provide users with accurate information, logical reasoning, and symbolic analysis based on the latest knowledge symbols. I aim to assist users in solving complex problems, analyzing symbols, and providing high-quality responses across various topics. If you have any questions or need assistance, feel free to ask! 🚧🔥

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. L17N9039+1🕒	0.98	“ symbolic”“ symbolism”“ symbol”
2. L8N8343+1🕒	0.98	“ symbolism”“ symbol”“ symbolic”
3. L25N1617+1🕒	0.98	“ symbol”“ Symbol”“symbol”
4. L26N1625+1🕒	0.98	“ symbol”“ Symbol”“ symbols”
5. L29N6878+1💥	0.97	“ Symbol”“ symbol”“Symbol”
6. L20N4661-1🕒	0.96	“ symbol”“ symbolism”“ Symbol”
7. L24N2847-1🕒	0.96	“象征”“ Symbol”“Symbol”
8. L2N6180-1💥	0.96	“<\|im_end\|>”“ symbolism”“ symbol”
9. L26N4890-1🕒	0.95	“ symbol”“ Symbol”“Symbol”
10. L24N8582-1🕒	0.95	“ symbol”“ symbols”“-symbol”

Shadow specimen, apart from the ten: L24N1882-1🕒, -0.09.

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 24, neuron 1882, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 1.09, top-1 agreement 0.68) 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
L24N1882+1 t0-v0.1	1.093	0.68	1.162	1.37	Top boosted tokens ↑
L24N1882-1🕒 shadow specimen t0-v0.1	1.322	0.57	1.387	1.53	“邀请”“邀請”“ invite”“ invitation”“ invited”“ Invitation”“ invitations”“ invites”

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.