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

 Known

-0.30

åį·

-0.28

åĲĪ

-0.27

 Derived

-0.26

By

-0.26

oz

-0.26

ocused

-0.25

çĦļçĥ§

-0.25

 oriented

-0.25

èĥĮ

-0.25

POSITIVE LOGITS

itra

0.31

æľīå¹¸

0.27

icum

0.27

seite

0.25

ä¸Ńåħ³

0.25

stretch

0.25

å¹¸ç¦ıæĦŁ

0.25

-thumb

0.24

 tÃ©r

0.24

swire

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.