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

 OTHERWISE

-0.25

èł¹

-0.25

"""č↵č↵

-0.24

 otherwise

-0.24

è°į

-0.24

 dend

-0.24

otherwise

-0.23

åı¦ä¸Ģ

-0.23

.TryGetValue

-0.23

cly

-0.23

POSITIVE LOGITS

ë¹Ļ

0.28

åĲĮæľŁ

0.26

 part

0.25

à¦Ľ

0.24

èģĺè¯·

0.24

çĦī

0.24

 Tits

0.23

blr

0.23

ICI

0.23

åħ¬æĬ¥

0.23

Activations Density 0.036%

No Known Activations

This feature has no known activations.