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

IGIN

-0.29

è¯Ŀè¯´

-0.28

credible

-0.26

PERT

-0.25

undry

-0.25

æīĵå¾Ĺ

-0.24

é«ĺãģĦ

-0.24

eneg

-0.23

å°Ĭ

-0.23

belt

-0.23

POSITIVE LOGITS

&amp

0.32

 tearDown

0.27

 mans

0.25

 sharing

0.25

.twitter

0.24

IRA

0.23

cene

0.23

sharing

0.23

angered

0.23

manda

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.