INDEX

Explanations

nan

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 discharged

-0.28

 Brain

-0.27

èµ¶æĿ¥

-0.26

sort

-0.25

iglia

-0.24

GetEnumerator

-0.24

 circulated

-0.24

 unleashed

-0.24

 directive

-0.24

 Circ

-0.24

POSITIVE LOGITS

èģĮ

0.27

åľĸçīĩ

0.26

åĽ¾çīĩ

0.25

minimum

0.25

æļĤ

0.25

pid

0.24

gif

0.24

*/č↵

0.24

linger

0.24

å²Ľ

0.24

Activations Density 0.055%

nan

No Comments

No Known Activations