INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸įå¹³è¡¡

-0.28

ighting

-0.27

ight

-0.26

ose

-0.26

ä¸Ģå¯¹

-0.26

ain

-0.26

unfinished

-0.25

åħļä¸Ńå¤®

-0.25

main

-0.25

å°»

-0.25

POSITIVE LOGITS

iesta

0.27

erville

0.26

Ã¡st

0.25

 denom

0.25

èĤļ

0.24

à´³

0.24

ÑĢÐµÐ±

0.23

Ã¬nh

0.23

Nik

0.23

Ranked

0.23

Activations Density 0.261%

No Known Activations

This feature has no known activations.