INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

Seeder

-0.28

oton

-0.27

ä»»æĢ§

-0.26

 impass

-0.25

 gran

-0.25

gig

-0.24

rbrace

-0.24

åĳĹ

-0.24

-picker

-0.24

è¾Ļ

-0.24

POSITIVE LOGITS

 juris

0.29

(pl

0.29

å¯¹éĿ¢

0.25

åĲİéĿ¢çļĦ

0.25

æŁ¥éĺħ

0.25

èĥĮåĲİçļĦ

0.25

 Oriental

0.24

_bits

0.24

||↵

0.24

unner

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.