INDEX

Explanations

of

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

ÑĤÐ²ÐµÑĢÐ¶Ð´Ð°

-0.27

auce

-0.25

lets

-0.25

 octave

-0.24

 wrought

-0.24

ï¸µ

-0.24

adier

-0.24

ivel

-0.24

éĢ¢

-0.24

çĽĳå¯Ł

-0.24

POSITIVE LOGITS

"=

0.27

å®«

0.24

atum

0.24

æīĵå¾Ĺ

0.24

nano

0.24

å®īå®ģ

0.24

ãģ¨è¨Ģãģ£ãģ¦

0.23

 íģ

0.23

 queues

0.23

"@

0.23

Activations Density 0.148%

of

No Comments

No Known Activations