INDEX

Explanations

legion

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç¢Ł

-0.26

å¸¦æĿ¥äºĨ

-0.25

å¼ķåıĳäºĨ

-0.25

éĩĳå±ŀ

-0.25

 fores

-0.25

éļ§

-0.25

åįļè§Ī

-0.24

å®Ī

-0.23

å¸¦æĿ¥

-0.23

 replicated

-0.23

POSITIVE LOGITS

eon

0.27

 editor

0.27

éĻĲ

0.27

åĵĦ

0.27

hta

0.27

/editor

0.26

 Editor

0.26

-II

0.26

Editor

0.25

heel

0.24

Activations Density 0.316%

legion

No Comments

No Known Activations