INDEX

Explanations

handheld electronic devices

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

Õª

-0.28

track

-0.25

OTO

-0.25

nosis

-0.24

 decision

-0.24

 matter

-0.24

 fores

-0.23

ç©¿

-0.23

 sinc

-0.23

nh

-0.23

POSITIVE LOGITS

airport

0.27

.esp

0.26

 bakery

0.25

akter

0.25

 LoginPage

0.25

acher

0.24

 enumerator

0.24

/weather

0.24

Airport

0.24

",(

0.24

Activations Density 0.002%

handheld electronic devices

No Comments

No Known Activations