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

åı£å¤´

-0.29

 Rand

-0.29

rand

-0.28

Row

-0.27

åĦ¿å¥³

-0.26

æīĢæīĢ

-0.26

æĭĻ

-0.26

 rand

-0.26

AGO

-0.26

mil

-0.26

POSITIVE LOGITS

ãģĵãģ¨ãģĮãģ§ãģį

0.26

serve

0.25

pery

0.23

ivirus

0.23

 obey

0.23

_ub

0.23

Ð³Ð»Ð°

0.23

èİ«æĸ¯

0.22

 Appeals

0.22

åĨ·

0.22

Activations Density 0.000%

No Known Activations

This feature has no known activations.