INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_None

-0.29

ç¥ī

-0.28

Ã¨s

-0.27

 Nail

-0.27

SCRIPT

-0.27

igest

-0.26

Ã©rie

-0.26

æĹ¶èĬĤ

-0.25

icer

-0.25

etails

-0.24

POSITIVE LOGITS

 fixed

0.33

 Fixed

0.26

ondo

0.26

.separator

0.26

åĪĨç¦»

0.25

.fixed

0.25

éĻ¢éķ¿

0.25

é¢ĨåħĪ

0.25

fixed

0.24

æıĲåĩºçļĦ

0.24

Activations Density 11.058%

No Known Activations

This feature has no known activations.