INDEX

Explanations

code, urls, and legal citations

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

åĩĨå¤ĩå¥½

-0.28

Fab

-0.28

æĺ¾

-0.28

ppt

-0.27

åħŃå¹´

-0.25

 ACTIONS

-0.25

xFB

-0.24

ä¸ĥå¹´

-0.24

Flo

-0.24

('__

-0.24

POSITIVE LOGITS

 Reds

0.26

nas

0.25

çĶ¥

0.25

 growth

0.24

ugins

0.24

rep

0.24

enos

0.24

 learning

0.23

nbsp

0.23

Activations Density 0.002%

code, urls, and legal citations

No Comments

No Known Activations