INDEX

Explanations

civil

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

 themselves

-0.31

éĴĿ

-0.27

obt

-0.27

cross

-0.27

 itself

-0.27

àª³

-0.26

 herself

-0.26

else

-0.25

est

-0.25

 cross

-0.25

POSITIVE LOGITS

rio

0.28

 sendData

0.27

å¯Ħ

0.26

å®īåħ¨ä¿Ŀéļľ

0.26

tableFuture

0.25

fact

0.25

edImage

0.25

èĩ£

0.25

 attaches

0.25

iggins

0.25

Activations Density 0.002%

civil

No Comments

No Known Activations