INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_30.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.30.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å®ļåĲĳ

-0.31

ilent

-0.30

æĹ¥æŃ£å¼ı

-0.29

picker

-0.27

esian

-0.26

à¤ĺ

-0.25

prep

-0.25

htdocs

-0.25

sticks

-0.25

æĺ±

-0.25

POSITIVE LOGITS

Ĥ¨

0.30

inde

0.28

åĪ°

0.28

 earned

0.28

 ventured

0.27

 realized

0.27

çĪŃ

0.27

æĮĽ

0.27

roman

0.27

oud

0.26

Activations Density 0.020%

No Known Activations

This feature has no known activations.