INDEX

Explanations

processes

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

èµĦæºĲä¼ĺåĬ¿

-0.27

 tileSize

-0.26

èµĦæºĲéħįç½®

-0.25

tile

-0.25

åľ¾

-0.24

æıĲæ¬¾

-0.24

ç¥¨

-0.24

 Ð¾Ð±Ð¾ÑĢ

-0.24

 figures

-0.24

.tie

-0.24

POSITIVE LOGITS

 process

0.58

è¿ĩç¨ĭ

0.54

 Process

0.44

process

0.43

éģİç¨ĭ

0.42

Process

0.41

_process

0.39

çļĦè¿ĩç¨ĭ

0.39

 proces

0.38

 processes

0.37

Activations Density 0.031%

processes

No Comments

No Known Activations