INDEX

Explanations

school

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

 damned

-0.26

 todd

-0.25

 Faster

-0.25

 damn

-0.25

credible

-0.25

 Synd

-0.24

 blasted

-0.24

TOR

-0.24

ze

-0.23

 speedy

-0.23

POSITIVE LOGITS

 Antworten

0.27

çĻ½èıľ

0.26

 rebound

0.25

aret

0.25

raits

0.24

 blind

0.24

otal

0.24

endet

0.23

æİ§åĪ¶ç³»ç»Ł

0.23

å·¥åİĤ

0.23

Activations Density 0.035%

school

No Comments

No Known Activations