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

çīĩåĪ»

-0.26

çļĦåĮºåĪ«

-0.25

å«īå¦Ĵ

-0.25

 MÃ¡

-0.24

ãĥļãĥ¼ãĤ¸

-0.24

 rivalry

-0.24

ä¸¾æĬ¥

-0.24

æĤ¨å¥½

-0.23

Ïį

-0.23

_REDIRECT

-0.23

POSITIVE LOGITS

ister

0.28

aised

0.27

DataMember

0.26

gÃ³

0.26

æīĢåľ¨åľ°

0.26

 NotImplementedError

0.26

ainter

0.25

_nil

0.25

ixer

0.25

 Liberals

0.25

Activations Density 0.066%

No Known Activations

This feature has no known activations.