INDEX

Explanations

di

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

çĥĤ

-0.27

resses

-0.26

resse

-0.25

å¿ĥçĸ¼

-0.24

æ´Ĺ

-0.24

 Aquarium

-0.23

çĽ¸å½ĵ

-0.23

æī¹åıĳå¸Ĥåľº

-0.23

çĽ¸çķ¶

-0.23

res

-0.23

POSITIVE LOGITS

åĢĻ

0.29

CA

0.27

riers

0.27

CA

0.27

 Scot

0.25

æ¸Ŀ

0.25

incr

0.25

çīĽèĤī

0.25

çĤ¸

0.25

rig

0.24

Activations Density 0.003%

di

No Comments

No Known Activations