INDEX

Explanations

to

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

 integer

-0.27

ublisher

-0.27

-feed

-0.25

ansen

-0.25

.getBytes

-0.25

 onStop

-0.25

ighting

-0.24

ngr

-0.24

_worker

-0.24

 broadcasting

-0.23

POSITIVE LOGITS

åį°

0.30

æ²¡äºĭ

0.26

æĺĤ

0.26

eor

0.25

alties

0.25

èĢ

0.24

æ¨¡èĮĥ

0.24

Ø±Ùģ

0.24

 promin

0.24

jours

0.23

Activations Density 0.002%

to

No Comments

No Known Activations