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

Negative Logits

éĽı

-0.27

nez

-0.26

mates

-0.26

umo

-0.26

iece

-0.26

 matter

-0.26

 factories

-0.25

jn

-0.25

ominated

-0.25

æ±ģ

-0.25

POSITIVE LOGITS

press

0.30

 Ariel

0.28

).__

0.26

shire

0.25

ISH

0.25

-bel

0.25

 Mavericks

0.25

PIP

0.24

Ð·Ð´

0.24

 airs

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.