INDEX

Explanations

gut

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

least

-0.29

ãĥ©ãĥ³ãĥī

-0.28

åı¶

-0.28

åı¶åŃĲ

-0.27

èµĽåĲİ

-0.26

 least

-0.26

åĪ¶éĢłåķĨ

-0.25

 DataView

-0.25

é¡¾

-0.24

çīĩéĿ¢

-0.24

POSITIVE LOGITS

Retention

0.29

commons

0.26

icious

0.25

æħ¥

0.25

osite

0.25

éķ¿å¯¿

0.25

 correl

0.25

æį

0.25

ä¸ºæĤ¨

0.25

èĬĿéº»

0.24

Activations Density 0.021%

gut

No Comments

No Known Activations