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

æīģ

-0.32

ardi

-0.32

äº²

-0.27

çŁŃæľŁåĨħ

-0.26

ì§ģ

-0.26

_alpha

-0.26

ITA

-0.25

 realized

-0.25

edException

-0.25

adero

-0.25

POSITIVE LOGITS

 scre

0.26

æī«çłģ

0.25

Pas

0.24

 rose

0.23

 colourful

0.23

çĨŁç»ĥ

0.23

åī¯æĢ»ç»ıçĲĨ

0.23

 Mash

0.23

 accordingly

0.22

ç¥ĿæĦ¿

0.22

Activations Density 0.006%

No Known Activations

This feature has no known activations.