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

_hold

-0.27

åĲĥ

-0.26

ompson

-0.26

aho

-0.25

 reimburse

-0.24

 lÃ²ng

-0.24

è¯Ŀè¯´

-0.24

inho

-0.24

MAS

-0.23

MAL

-0.23

POSITIVE LOGITS

ç¬¥

0.29

æıĲåıĸ

0.26

.Framework

0.25

partials

0.25

æŀķ

0.24

keletal

0.24

æĪ³

0.24

extract

0.24

åĢ¬

0.24

 Frames

0.24

Activations Density 0.026%

No Known Activations

This feature has no known activations.