INDEX

Explanations

weigh

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

ãĤ±ãĥĥãĥĪ

-0.29

åıĳ

-0.28

endir

-0.27

rides

-0.27

ending

-0.25

 McCart

-0.25

 paired

-0.24

 rides

-0.24

æĮ¤

-0.24

Shr

-0.24

POSITIVE LOGITS

ç»ĵæŀĦæĢ§

0.28

-widgets

0.26

 consc

0.26

åīģ

0.25

dere

0.25

Ã¡cil

0.24

'::

0.23

 crossword

0.23

äºīè®º

0.23

çŃ

0.23

Activations Density 0.001%

weigh

No Comments

No Known Activations