INDEX

Explanations

code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

ä¼łå¯¼

-0.31

nea

-0.29

 Present

-0.28

_present

-0.27

.present

-0.27

æī¾

-0.27

 Rossi

-0.27

eni

-0.26

ORY

-0.26

neas

-0.26

POSITIVE LOGITS

hal

0.28

æĪĳåİ»

0.26

hal

0.25

_suffix

0.25

æĸĩç«łæĿ¥æºĲ

0.25

_integration

0.24

åŀŃ

0.23

ogl

0.23

è°Īèµ·

0.23

Hal

0.23

Activations Density 0.101%

code

No Comments

No Known Activations