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

ÙĩØ©

-0.27

erais

-0.27

orra

-0.26

pecially

-0.26

ä¸ºä¸»

-0.26

pike

-0.25

 thunk

-0.24

 salute

-0.24

_REASON

-0.23

åħ±åĴĮ

-0.23

POSITIVE LOGITS

igue

0.29

å¥½äºĨ

0.27

ifu

0.26

iska

0.25

ild

0.25

iple

0.24

å¼ĢåĲ¯äºĨ

0.24

 unravel

0.24

.pick

0.23

åħ³äºİæĪĳä»¬

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.