INDEX

Explanations

Small numbers

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¿ĥçĲĨ

-0.26

Ä±ÅŁÄ±

-0.25

èĲ½åľ¨

-0.25

 ÑĩÐµÐ»

-0.25

éĺį

-0.24

Domain

-0.24

slack

-0.24

ç³ľ

-0.24

çļĦåĲĪä½ľ

-0.24

 Capacity

-0.23

POSITIVE LOGITS

silent

0.27

åľŃ

0.26

up

0.26

Ã³Å¼

0.26

 raised

0.26

 cast

0.26

åħ¼

0.26

 silent

0.25

 synonym

0.24

ä¸ĢåĲĳ

0.24

Activations Density 1.824%

Small numbers

No Comments

No Known Activations