INDEX

Explanations

foot

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

rig

-0.27

licative

-0.27

 dÃº

-0.27

æ·ĭ

-0.26

Sample

-0.26

åĪģ

-0.25

å¼Ģåħ³

-0.24

æĮ

-0.24

Ð²Ñĭ

-0.24

pliers

-0.24

POSITIVE LOGITS

 differentiated

0.26

æĸ¯åŁº

0.26

theid

0.26

äº¤ä¼ļ

0.25

çļĦä¸Ģå¤§

0.25

(?:

0.25

-Smith

0.25

mÃ¡t

0.25

ropy

0.24

<![

0.24

Activations Density 0.001%

foot

No Comments

No Known Activations