INDEX

Explanations

handsome

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

TK

-0.25

ates

-0.25

orget

-0.24

Jos

-0.24

 building

-0.24

Tag

-0.23

Rew

-0.23

ots

-0.23

æĢ»éĩı

-0.23

å¤ľéĹ´

-0.23

POSITIVE LOGITS

åĲ¬ä¼Ĺ

0.28

thur

0.26

angular

0.25

>",

0.25

 cleared

0.24

 isAuthenticated

0.24

 amor

0.24

 ApplicationContext

0.24

icz

0.23

å¼

0.23

Activations Density 0.002%

handsome

No Comments

No Known Activations