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

 appropriate

-0.27

unl

-0.27

åĲĪ

-0.27

appropriate

-0.27

éĢĤå½ĵ

-0.26

 appropriated

-0.26

 intermedi

-0.25

arem

-0.25

è¿Ľåħ¥åĪ°

-0.25

 qual

-0.24

POSITIVE LOGITS

rones

0.26

ä½ľä¸ļ

0.25

AGON

0.24

ä¸ĩå®¶

0.24

_MR

0.24

åºĸ

0.24

AndWait

0.24

.fromJson

0.24

xAE

0.23

è·Ŀ

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.