INDEX

Explanations

”

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ater

-0.30

ATER

-0.29

aters

-0.28

olated

-0.27

CS

-0.27

Measured

-0.26

éĥ½ä¼ļæľī

-0.26

||=

-0.26

overn

-0.25

mtree

-0.25

POSITIVE LOGITS

dued

0.26

lify

0.24

 coll

0.24

åħ¨

0.23

çĶ²çĬ¶

0.23

arr

0.23

åĨįä¸Ģæ¬¡

0.23

 cerr

0.23

åĨįæ¬¡

0.23

åıĮ

0.23

Activations Density 0.002%

”

No Comments

No Known Activations