INDEX

Explanations

Russian text

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

æľį

-0.30

loat

-0.26

*@

-0.26

No

-0.26

è¿Ķä¹¡

-0.25

 Median

-0.24

íĨµ

-0.24

UILD

-0.24

 Sylvia

-0.24

 Other

-0.23

POSITIVE LOGITS

pragma

0.31

ousel

0.26

Ã§i

0.26

posix

0.26

 closures

0.25

dee

0.25

 closure

0.25

isme

0.24

pos

0.24

closure

0.24

Activations Density 0.001%

Russian text

No Comments

No Known Activations