INDEX

Explanations

Vir

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

amment

-0.30

iest

-0.28

aud

-0.27

ause

-0.27

 constr

-0.27

cheid

-0.27

ollo

-0.26

loom

-0.26

Ã¡sa

-0.26

aur

-0.25

POSITIVE LOGITS

 scrambling

0.27

-sc

0.26

æĬĦè¢Ń

0.25

bub

0.25

ghi

0.25

_SCR

0.24

 scattering

0.24

.bundle

0.24

 Clan

0.23

å¹³æ·¡

0.23

Activations Density 0.006%

Vir

No Comments

No Known Activations