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

 cris

-0.31

nings

-0.27

éĺĻ

-0.25

æ¢³

-0.24

æīĢåľ¨

-0.24

ÃĸZ

-0.23

erset

-0.23

æ±¾

-0.23

 unarmed

-0.22

 usual

-0.22

POSITIVE LOGITS

otlin

0.25

ASTE

0.25

 mand

0.25

vari

0.24

atedRoute

0.24

 implant

0.24

choose

0.24

äºı

0.24

 Gloria

0.24

 guilt

0.23

Activations Density 0.007%

No Known Activations

This feature has no known activations.