INDEX

Explanations

birth

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

moo

-0.28

å³ª

-0.27

çĦ¶æĺ¯

-0.27

ä¼Ĭæĭī

-0.26

éľ¹

-0.25

à´¦

-0.25

idal

-0.25

çĴ©

-0.25

ourced

-0.25

ocities

-0.25

POSITIVE LOGITS

æĸ°å¼Ģ

0.34

ps

0.31

orman

0.27

sem

0.27

 onBindViewHolder

0.26

tm

0.26

æĢĢ

0.25

pm

0.25

ä¸»è§Ĥ

0.25

 creatively

0.24

Activations Density 0.016%

birth

No Comments

No Known Activations