INDEX

Explanations

FIT

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çĭ

-0.30

çĭŃ

-0.28

åĶ®

-0.28

agus

-0.27

nÃ¼

-0.26

bios

-0.26

(ret

-0.25

èŀĪ

-0.25

 retract

-0.25

 Indy

-0.25

POSITIVE LOGITS

Catch

0.29

catch

0.29

çªģçł´

0.26

 beyond

0.26

 breakpoint

0.26

æ·¤

0.26

 catches

0.25

æ±

0.25

 catch

0.25

bast

0.25

Activations Density 0.002%

FIT

No Comments

No Known Activations