INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_35.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.35.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IPA

-0.28

gage

-0.28

æīįèĥ½

-0.28

çļĦè§Ĵèī²

-0.27

 role

-0.27

arine

-0.26

subs

-0.24

çļĦéŃħåĬĽ

-0.24

åĿĬ

-0.24

tape

-0.24

POSITIVE LOGITS

_mx

0.28

æ¾¤

0.25

EFF

0.25

 chÃ¡y

0.24

ĥģ

0.24

å¯¤

0.24

COME

0.24

.Def

0.24

åĩłå®¶

0.23

kus

0.23

Activations Density 34.822%

No Known Activations

This feature has no known activations.