INDEX

Explanations

programming code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

åį»

-0.28

åį´

-0.26

åħĥå·¦åı³

-0.25

ysis

-0.25

appe

-0.24

rice

-0.24

track

-0.24

tract

-0.24

å±¯

-0.24

__(

-0.23

POSITIVE LOGITS

èŁĴ

0.26

gles

0.25

vens

0.25

nable

0.24

éĴĹ

0.24

avirus

0.24

 Bands

0.23

 urlencode

0.23

setProperty

0.23

gien

0.23

Activations Density 37.894%

programming code

No Comments

No Known Activations