INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.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

rott

-0.28

agrams

-0.28

atÃ³

-0.26

@class

-0.26

æħķ

-0.26

æĭ®

-0.26

 Gifts

-0.25

Zag

-0.25

 Coupons

-0.25

 Incre

-0.24

POSITIVE LOGITS

 authoritative

0.27

orn

0.26

shr

0.25

lical

0.25

 post

0.25

lac

0.25

à¸§à¸²à¸ĩà¹ģà¸ľà¸Ļ

0.24

gulp

0.24

pac

0.24

amba

0.24

Activations Density 0.041%

No Known Activations

This feature has no known activations.