INDEX

Explanations

which

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

argent

-0.33

.initState

-0.31

æľ¬

-0.26

è·¨å¢ĥ

-0.25

-init

-0.25

èľĴ

-0.25

 OUTER

-0.25

xFE

-0.25

 contents

-0.24

åħĪå¤©

-0.24

POSITIVE LOGITS

èĩ³å°Ĭ

0.27

andum

0.26

obuf

0.26

æľīæķĪçļĦ

0.26

)e

0.26

åĲİæİĴ

0.25

pij

0.24

console

0.24

ç´łé£Ł

0.24

Filters

0.23

Activations Density 0.005%

which

No Comments

No Known Activations