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

ï¸µ

-0.29

ATS

-0.29

 khÃºc

-0.28

ava

-0.27

ado

-0.25

aits

-0.25

anut

-0.25

orns

-0.25

nÃ©e

-0.25

åĴĻ

-0.24

POSITIVE LOGITS

por

0.28

ortal

0.26

sent

0.26

èĢĮä¸į

0.26

SENT

0.25

å¹³åĿĩ

0.25

Cy

0.25

æĤ¼

0.24

 averages

0.24

graphs

0.24

Activations Density 0.014%

No Known Activations

This feature has no known activations.