INDEX

Explanations

Code and comments

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

auge

-0.28

uum

-0.26

åı¸

-0.26

ç¹

-0.25

alc

-0.25

å¤ĩ

-0.25

 Flem

-0.24

fly

-0.24

osaic

-0.24

kees

-0.24

POSITIVE LOGITS

_Instance

0.28

ä¸įå¹¸

0.28

çĲĨä¼ļ

0.27

 Canyon

0.27

spender

0.27

 eater

0.26

å¿§èĻĳ

0.26

è±Ĳå¯Į

0.25

èį©

0.25

xab

0.24

Activations Density 0.011%

Code and comments

No Comments

No Known Activations