INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

akan

-0.27

æĬĢå¸Ī

-0.26

Dub

-0.26

 Rent

-0.25

kie

-0.25

Ð¼Ñı

-0.25

 Dress

-0.24

vens

-0.24

-score

-0.24

 Housing

-0.23

POSITIVE LOGITS

åłķ

0.28

inheritdoc

0.28

æĬķåħ¥åĪ°

0.26

 trunc

0.26

 freder

0.25

StackSize

0.25

pile

0.24

åħľ

0.24

dirty

0.24

Participant

0.23

Activations Density 0.031%

No Known Activations

This feature has no known activations.