INDEX

Explanations

lit

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_30.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.30.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

py

-0.26

dat

-0.26

CRE

-0.26

cre

-0.25

åĪ¨

-0.24

ä¿¡æģ¯æĬ«éľ²

-0.24

Ã©al

-0.24

clo

-0.24

 grund

-0.24

Cre

-0.24

POSITIVE LOGITS

 Static

0.30

Bars

0.28

ronic

0.27

Static

0.27

 retros

0.26

 STATIC

0.26

 EXPER

0.25

agine

0.25

åĳµ

0.24

omore

0.24

Activations Density 0.104%

lit

No Comments

No Known Activations