INDEX

Explanations

looked

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

YLON

-0.31

ITO

-0.27

 london

-0.26

Rev

-0.25

hone

-0.24

ÐµÑĢÑĮ

-0.24

 Numero

-0.23

Ð¿Ñĭ

-0.23

_numero

-0.23

ä¼ı

-0.23

POSITIVE LOGITS

hel

0.29

 those

0.28

 cath

0.28

éĥ¨éķ¿

0.27

mel

0.27

those

0.26

uiltin

0.25

ä¸įè§£

0.25

uds

0.24

åĨħç½®

0.24

Activations Density 0.004%

looked

No Comments

No Known Activations