INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-vers

-0.31

cop

-0.30

zem

-0.29

oud

-0.27

 Vers

-0.27

æĪĲä»½

-0.26

æĪĲåĪĨ

-0.26

 maxi

-0.26

ophobia

-0.25

 Maver

-0.25

POSITIVE LOGITS

lib

0.28

 mistake

0.26

Lib

0.26

self

0.25

 bowl

0.24

lib

0.24

 self

0.24

 barred

0.24

tip

0.24

binations

0.24

Activations Density 0.012%

No Known Activations

This feature has no known activations.