INDEX

Explanations

programming code

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

 Yugoslavia

-0.29

ador

-0.27

æµĲ

-0.26

 haus

-0.25

æŃ§è§Ĩ

-0.24

 cuckold

-0.24

imid

-0.24

(UnityEngine

-0.24

Sim

-0.23

yuk

-0.23

POSITIVE LOGITS

é¥±åĴĮ

0.27

getto

0.27

closed

0.26

edException

0.25

è¿ĳè·Ŀç¦»

0.25

getRepository

0.25

 closed

0.25

.closed

0.24

çĩĥ

0.24

ellular

0.24

Activations Density 0.007%

programming code

No Comments

No Known Activations