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

ego

-0.30

çī¹å®ļ

-0.28

 Specific

-0.27

 spÃ©cifique

-0.27

unique

-0.25

Discover

-0.25

Appear

-0.25

 Discover

-0.25

 unique

-0.25

sehen

-0.24

POSITIVE LOGITS

ä¿ĥ

0.27

å®¢æ°Ķ

0.26

ä½ıåľ¨

0.26

å§Ķä¼ļ

0.25

 woke

0.25

-console

0.24

 third

0.24

Ð°Ð½Ð³

0.23

çĨŁæĤīçļĦ

0.23

 realism

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.