INDEX

Explanations

refrigerator

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸ĢçĤ¹

-0.27

é¡¶ç«¯

-0.25

OTE

-0.25

éģ£

-0.24

sor

-0.24

 speculative

-0.24

aho

-0.24

 Dynamic

-0.24

 demo

-0.23

Fus

-0.23

POSITIVE LOGITS

anton

0.27

-script

0.26

quÃ©

0.26

åĮħåŃĲ

0.26

idUser

0.25

idor

0.24

 ordained

0.24

æĭĶ

0.24

STRU

0.24

 verst

0.24

Activations Density 0.267%

refrigerator

No Comments

No Known Activations