INDEX

Explanations

from

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

cff

-0.33

ä¸Ģå®¶

-0.29

deaux

-0.26

 plank

-0.26

æĶ¹éĿ©åĪĽæĸ°

-0.26

hÃ©

-0.25

trait

-0.25

æĵ¦

-0.25

 laps

-0.25

 trait

-0.24

POSITIVE LOGITS

éĶ»éĢł

0.27

.dup

0.24

 freopen

0.24

_simps

0.24

upe

0.24

_NOP

0.23

	freopen

0.23

æ³³

0.23

_vue

0.22

 scho

0.22

Activations Density 0.002%

from

No Comments

No Known Activations