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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Mission

-0.26

é«ĺä½į

-0.25

åĵº

-0.25

ä¼ļåıĳçĶŁ

-0.24

—to

-0.24

æĿĵ

-0.24

ä¸´

-0.24

ello

-0.23

ä¸įçķĻ

-0.23

ymous

-0.23

POSITIVE LOGITS

]("

0.27

 venues

0.25

åĳĬ

0.25

 spikes

0.24

presso

0.24

integration

0.23

iks

0.23

 integration

0.23

 pill

0.23

bilt

0.23

Activations Density 0.005%

No Known Activations

This feature has no known activations.