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

 Revolutionary

-0.28

(::

-0.27

çıĻ

-0.27

idis

-0.27

 sacrificed

-0.26

foundland

-0.26

bens

-0.25

clud

-0.25

 Lith

-0.24

ledge

-0.24

POSITIVE LOGITS

uh

0.28

icast

0.26

åįıä¼ļä¼ļåĳĺ

0.26

Ire

0.26

ic

0.25

zo

0.25

ye

0.24

DU

0.24

InstanceOf

0.24

ZO

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.