INDEX

Explanations

scientific/medical language

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

nist

-0.27

è´¯å½»èĲ½å®ŀ

-0.26

cer

-0.25

æĸ¹æĸ¹éĿ¢éĿ¢

-0.25

_virtual

-0.24

thed

-0.24

Ike

-0.24

forgot

-0.24

unp

-0.24

ipp

-0.24

POSITIVE LOGITS

quil

0.28

ank

0.27

ç½ķ

0.27

SEM

0.26

rÃŃ

0.26

/renderer

0.26

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

0.25

rador

0.24

è½®å»ĵ

0.24

à¹Īà¸²à¸¢

0.24

Activations Density 0.002%

scientific/medical language

No Comments

No Known Activations