INDEX

Explanations

athed

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

unate

-0.30

Ø¨Ø³

-0.28

 Curl

-0.26

vs

-0.24

é©±åĬ¨

-0.24

ãģ£ãģ

-0.24

 Cout

-0.23

rem

-0.23

 needed

-0.23

ize

-0.23

POSITIVE LOGITS

OptionsMenu

0.28

otch

0.25

reed

0.25

_IMPORTED

0.24

è½»

0.24

issance

0.24

CHAN

0.24

 Moderator

0.24

åĻ¢

0.24

amar

0.23

Activations Density 0.000%

athed

No Comments

No Known Activations