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

chap

-0.29

 arty

-0.27

lint

-0.26

hev

-0.26

è½¬è½½è¯·

-0.25

 chap

-0.25

é¸¡æ±¤

-0.25

 royalty

-0.24

æľīéĴ±

-0.24

arma

-0.24

POSITIVE LOGITS

åħļå§Ķ

0.27

åĳ±

0.26

 spacing

0.26

ful

0.25

HTTPRequest

0.24

 spinning

0.24

èħ¹éĥ¨

0.24

$config

0.24

 cellspacing

0.24

BOSE

0.24

Activations Density 10.011%

No Known Activations

This feature has no known activations.