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

EXT

-0.28

cision

-0.24

/vnd

-0.24

ESPN

-0.24

 prol

-0.24

segment

-0.24

å«ļ

-0.23

 preorder

-0.23

plet

-0.23

promotion

-0.23

POSITIVE LOGITS

_false

0.28

 undef

0.27

è§Ħæ¨¡

0.26

èĢģå¸ĪçļĦ

0.26

ueva

0.26

ona

0.26

FO

0.26

åŃ¦ä¹ł

0.25

æ²¹

0.25

esh

0.25

Activations Density 0.000%

No Known Activations

This feature has no known activations.