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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å°ıç±³

-0.31

éļĲ

-0.27

Plain

-0.26

æ¤ħ

-0.26

ersistence

-0.25

éļĲå½¢

-0.25

leitung

-0.24

lington

-0.24

ç¨³å®ļçļĦ

-0.24

å¾ªçİ¯

-0.24

POSITIVE LOGITS

atk

0.26

èĪįå¾Ĺ

0.26

ycop

0.26

cam

0.25

ypi

0.24

 tÃ¶

0.24

irement

0.24

Swe

0.24

zp

0.23

ABCDE

0.23

Activations Density 0.007%

No Known Activations

This feature has no known activations.