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

/jpeg

-0.26

à¸¸à¸¡

-0.26

-bedroom

-0.25

_FLAG

-0.25

YO

-0.24

éĴ´

-0.24

(tm

-0.24

=item

-0.23

.setSelection

-0.23

FLAG

-0.23

POSITIVE LOGITS

åĩĨ

0.29

ä»İä¸ļèĢħ

0.27

ä¹ħäºĨ

0.27

 contraction

0.26

å°½å¤´

0.25

æľ«

0.25

èĩªæĿ¥

0.24

_sections

0.24

 educated

0.24

 Wade

0.24

Activations Density 0.029%

No Known Activations

This feature has no known activations.