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

 Kara

-0.25

æ££

-0.25

 british

-0.25

å¤§å®¶åĪĨäº«

-0.24

 reluctance

-0.23

è©±

-0.23

'.

-0.23

brit

-0.22

-bre

-0.22

æİ¥

-0.22

POSITIVE LOGITS

elles

0.30

etu

0.28

_PRIVATE

0.28

æį

0.26

enses

0.26

 escalating

0.25

illes

0.25

 Â±

0.25

empl

0.24

ega

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.