INDEX

Explanations

URLs and code

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

rowing

-0.29

å¯¹è¯¥

-0.27

ths

-0.25

arta

-0.25

ignet

-0.24

<small

-0.23

 starters

-0.23

oning

-0.23

ÅĦski

-0.23

",-

-0.23

POSITIVE LOGITS

vant

0.28

ek

0.27

 Anthrop

0.26

åı£

0.26

åĵ®

0.25

 lá»£i

0.25

yz

0.24

èĸĦå¼±

0.24

 Polly

0.24

 remote

0.24

Activations Density 0.785%

URLs and code

No Comments

No Known Activations