INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inator

-0.30

ä¹ĭä½ľ

-0.29

bel

-0.26

uhan

-0.26

ang

-0.25

inging

-0.25

ctl

-0.25

dan

-0.25

idge

-0.24

 //}↵

-0.24

POSITIVE LOGITS

ickers

0.30

ç±³åħ°

0.27

amu

0.27

åĪĽæĦı

0.27

ç¼İ

0.26

AM

0.25

ÙĦØ³

0.25

Ø±Øµ

0.25

reuse

0.24

anks

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.