INDEX

Explanations

see

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çĶ³

-0.28

ãĤ¤ãĤ¹

-0.27

usa

-0.26

.readString

-0.26

 minHeight

-0.26

æŃ£å¸¸ä½¿çĶ¨

-0.26

ajas

-0.25

igram

-0.25

aris

-0.24

-CS

-0.24

POSITIVE LOGITS

keiten

0.25

defgroup

0.25

it

0.24

 sidelines

0.24

è¿ĺåľ¨

0.24

ä¸Ģè§Ī

0.23

orph

0.23

qua

0.23

éĴĪå¯¹æĢ§

0.23

until

0.23

Activations Density 3.183%

see

No Comments

No Known Activations