INDEX

Explanations

assistance

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

dens

-0.30

èī¯

-0.29

åĩłä½ķ

-0.28

å«Į

-0.27

è¿ĻçĤ¹

-0.27

frag

-0.26

å·¥åİĤ

-0.26

 Ð¼Ð°ÑģÑĤ

-0.25

nth

-0.25

åıĭ

-0.25

POSITIVE LOGITS

oe

0.33

imes

0.25

tail

0.25

æĤ¬æĮĤ

0.25

 tails

0.25

 tail

0.25

 toward

0.25

 Learned

0.25

ta

0.24

inkle

0.24

Activations Density 0.004%

assistance

No Comments

No Known Activations