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

 Formation

-0.27

¢åįķ

-0.27

ãĥ¼ãĤº

-0.27

Formation

-0.26

 hanging

-0.26

é¬

-0.25

 formation

-0.25

Ð¾ÐºÐ¾

-0.25

REW

-0.24

æĳĩå¤´

-0.24

POSITIVE LOGITS

è¿ĻéĩĮçļĦ

0.30

éľį

0.27

å±¥

0.27

è¿Ļ

0.27

 porr

0.27

åĪ°è¿ĻéĩĮ

0.27

ëŁ¬

0.27

 mistr

0.26

æŃ¤å¤Ħ

0.25

äºĭ

0.25

Activations Density 0.015%

No Known Activations

This feature has no known activations.