INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

ÐµÐ²Ð°

-0.27

otts

-0.24

hoff

-0.24

 sidel

-0.24

æĥ³èµ·äºĨ

-0.24

åľ¨åºĬä¸Ĭ

-0.24

éģĶ

-0.24

æĬĵæįķ

-0.23

 squirt

-0.23

åĢĴåľ¨åľ°

-0.23

POSITIVE LOGITS

éĵ

0.28

anship

0.27

eting

0.27

ncia

0.26

addChild

0.25

lik

0.25

.lifecycle

0.25

arent

0.25

icum

0.24

ä¸ĢåŃĹ

0.24

Activations Density 0.031%

No Known Activations

This feature has no known activations.