INDEX

Explanations

link

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

ç»¯

-0.30

wal

-0.28

è¯Ŀé¢ĺ

-0.26

>Main

-0.25

ÑĥÐ¶

-0.24

setProperty

-0.24

æ³£

-0.24

oret

-0.23

å¥½æľĭåıĭ

-0.23

zes

-0.23

POSITIVE LOGITS

éĸ£

0.28

 further

0.28

richt

0.27

dav

0.27

éĺģ

0.25

al

0.25

 polys

0.24

'.'

0.24

è¿Ľä¸ĢæŃ¥

0.24

panels

0.23

Activations Density 0.009%

link

No Comments

No Known Activations