INDEX

Explanations

make

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

agn

-0.26

ohana

-0.26

 nodeName

-0.25

åŃĢ

-0.25

 razÃ³n

-0.25

èĲ½ä¸ĭ

-0.24

 sentences

-0.24

Eag

-0.24

èīĭ

-0.23

>('

-0.23

POSITIVE LOGITS

èĬľ

0.28

 Cristiano

0.28

ador

0.27

 ÑĤÐ¾Ð¶

0.27

rist

0.26

 lyric

0.26

Diamond

0.25

Spot

0.25

é¾Ī

0.25

Appro

0.25

Activations Density 0.002%

make

No Comments

No Known Activations