INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

ÃŃcio

-0.28

å¤§éħĴåºĹ

-0.28

 Conway

-0.25

å¤§å®Ĺ

-0.25

ocio

-0.25

arian

-0.24

 AssemblyVersion

-0.24

ifu

-0.24

 Kawasaki

-0.24

æ³Ľ

-0.23

POSITIVE LOGITS

 outr

0.29

ç¬ĳçĿĢ

0.26

 recommand

0.26

 fucked

0.25

é²

0.25

éĻĦä»¶

0.25

 halluc

0.24

-containing

0.24

 hunt

0.24

 \↵↵

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.