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

 terms

-0.29

-0.28

 inequality

-0.28

-0.27

pk

-0.26

çĦī

-0.26

 rights

-0.25

 mixed

-0.24

 parentheses

-0.24

POSITIVE LOGITS

íĹĢ

0.29

ousel

0.27

oppel

0.27

ildo

0.26

ì¤«

0.26

 ãĥĪãĥ©ãĥĥãĤ¯

0.25

zell

0.25

ë´£

0.25

 hookup

0.24

 WARRANTY

0.24

Activations Density 0.004%

No Known Activations

This feature has no known activations.