INDEX

Explanations

Names

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

roid

-0.26

-hop

-0.26

 colleges

-0.26

 Simply

-0.25

Ø±Ø§ÙĤ

-0.25

é«¯

-0.25

æį¢

-0.25

hop

-0.24

ippers

-0.24

 simply

-0.24

POSITIVE LOGITS

åıįåºĶ

0.31

zell

0.27

åĪĨä¼ļ

0.26

 FEMA

0.25

Naming

0.24

æĪ·åı£

0.24

CardBody

0.24

-functional

0.24

 react

0.24

Stroke

0.24

Activations Density 0.003%

Names

No Comments

No Known Activations