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

é£İåı£

-0.27

ä»Ģä¹Īäºĭ

-0.27

SI

-0.26

hi

-0.26

çŁ³æ²¹åĮĸå·¥

-0.26

ä¿ĿæĬ¤

-0.24

 cuid

-0.24

alach

-0.24

dan

-0.24

ä¾

-0.24

POSITIVE LOGITS

 infra

0.28

ArrayType

0.28

leness

0.27

icture

0.27

Ð·Ð½Ð°Ðº

0.26

æŀļ

0.25

ÙĬØ±Ø©

0.24

 shade

0.24

++.

0.24

æĢı

0.24

Activations Density 0.057%

No Known Activations

This feature has no known activations.