INDEX

Explanations

size, comparison

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

-0.30

Hud

-0.25

 Benjamin

-0.25

ful

-0.25

Â½

-0.24

åĪ°åºķ

-0.24

ol

-0.24

 Term

-0.23

ful

-0.23

bull

-0.23

POSITIVE LOGITS

-Jul

0.29

é©¸

0.27

cedure

0.26

snd

0.25

izzer

0.25

ablish

0.25

pies

0.25

ä¸ŃåŃĺåľ¨çļĦ

0.24

è®¹

0.24

tÄħ

0.24

Activations Density 0.000%

size, comparison

No Comments

No Known Activations