INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

ForKey

-0.28

 natives

-0.26

å¤§éģĵ

-0.26

iations

-0.24

atti

-0.24

æĢµ

-0.24

orra

-0.24

 derives

-0.24

è·ª

-0.24

æ°ĳæĹıæĸĩåĮĸ

-0.24

POSITIVE LOGITS

 Urban

0.30

enge

0.27

Verdana

0.26

_LOCATION

0.25

 NoSuchElementException

0.25

 Bloom

0.24

åĬłçĽĸ

0.24

Jim

0.24

Mat

0.24

iron

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.