INDEX

Explanations

height

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

 BufferedReader

-0.29

/train

-0.28

 Scenes

-0.27

 Verse

-0.26

ourd

-0.26

éĽĩ

-0.26

lane

-0.26

/************************************************************************

-0.26

 Apprent

-0.25

é¦ĸéĢī

-0.25

POSITIVE LOGITS

 arms

0.31

abi

0.28

æĮ

0.27

ipple

0.27

azz

0.26

uchi

0.26

owers

0.25

 tomb

0.25

ooke

0.25

 cach

0.24

Activations Density 0.013%

height

No Comments

No Known Activations