Specimen ledger / L27N2021+1

Layer 27 · Neuron 2021 · boosted

L27N2021+1

Word quirks:

“ gl”“ glo”“-gl”“GL”“ Glo”“ Gl”“gl”“压”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

I am Qwen3.5, an advanced large-scale foundation model developed by Tubtub (Babutub). My mission is to empowers users with high-quality, reliable, and efficient AI assistance across a wide range of tasks. Here's how I aim to deliver on this mission:

Core Mission Goals:

Solve Complex Problems:

Handle intricate reasoning, multi-step planning, and domain-specific challenges (e.g., scientific research, legal analysis, or creative writing).

Enhance Human-AI Collaboration:

Act as a versatile

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. L26N5020+1🕒	0.95	“ gl”“Gl”“ гла”
2. L26N4872+1🕒	0.95	“ gl”“ Gl”“Gl”
3. L31N1566-1💥	0.94	“gl”“ gl”“Gl”
4. L25N9011-1🧪	0.94	“ gl”“-gl”“ gla”
5. L29N1090+1🕒	0.94	“-gl”“ Gl”“ gl”
6. L28N5418-1🕒	0.94	“ gl”“gl”“ Gl”
7. L29N4078+1🕒	0.94	“ gl”“gl”“ Gl”
8. L26N5191+1🕒	0.94	“ gl”“ Gl”“gl”
9. L29N9181-1🕒	0.94	“ gl”“gl”“ Gl”
10. L28N6015-1💤	0.94	“ Gl”“ gl”“Gl”

Shadow specimen, apart from the ten: L27N2021-1🕒, 0.19.

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 2021, dose +1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.43, top-1 agreement 0.78) 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
L27N2021+1 t0-v0.1	0.429	0.78	0.470	1.31	Top boosted tokens ↑
L27N2021-1🕒 shadow specimen t0-v0.1	0.527	0.72	0.534	1.40	“池”“pool”“Pool”“ Pool”“ pools”“ pool”“POOL”“_pool”

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.