INDEX

Explanations

carrots

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥ³ãĤ°

-0.30

eyed

-0.30

çĪ½

-0.29

ere

-0.28

-running

-0.27

åĪ¤æĸŃ

-0.26

 Judgment

-0.26

 sondern

-0.26

æĭ³å¤´

-0.25

çļĦçĽ®åħī

-0.24

POSITIVE LOGITS

ç§£

0.28

(extra

0.26

åľŁè±Ĩ

0.26

/autoload

0.25

 Dean

0.25

åĨľåī¯

0.25

ynamo

0.24

 inde

0.24

cth

0.24

 Corinth

0.24

Activations Density 0.001%

carrots

No Comments

No Known Activations