INDEX

Explanations

while

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

/mat

-0.28

sym

-0.27

_observer

-0.27

.opens

-0.27

éĢģåĩº

-0.26

 scram

-0.26

æ¦ĤåĨµ

-0.26

'#{

-0.26

ammen

-0.25

åĮ¹

-0.25

POSITIVE LOGITS

lse

0.28

@stop

0.26

 behavior

0.26

.Tables

0.26

POSITE

0.25

è¡Įä¸º

0.24

tables

0.24

çİ¯ç»ķ

0.24

icopter

0.24

 Behavior

0.24

Activations Density 0.550%

while

No Comments

No Known Activations