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

 onItemClick

-0.29

å¼ĢæĿ¥

-0.28

åŃµåĮĸåĻ¨

-0.28

 XmlDocument

-0.26

ammen

-0.26

arial

-0.26

ecom

-0.25

{{{

-0.25

 dodge

-0.24

icator

-0.24

POSITIVE LOGITS

qui

0.30

--

0.29

åĴĮæľįåĬ¡

0.29

gn

0.28

itos

0.28

pu

0.26

uras

0.26

fter

0.26

quete

0.26

 today

0.25

Activations Density 0.007%

No Known Activations

This feature has no known activations.