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

eba

-0.29

Intermediate

-0.28

æĺĵ

-0.27

ä¸ŃéĹ´

-0.27

allen

-0.26

bay

-0.26

amp

-0.26

 even

-0.25

 belt

-0.25

å½ĵä¹ĭ

-0.25

POSITIVE LOGITS

ÐºÐ°ÑĢ

0.30

ograms

0.27

urning

0.27

asts

0.25

histor

0.25

/history

0.25

 trÆ°ng

0.25

ojis

0.24

å¹²åĺĽ

0.24

dings

0.24

Activations Density 0.029%

No Known Activations

This feature has no known activations.