INDEX

Explanations

to

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

SEM

-0.27

 Dict

-0.27

amed

-0.25

ilha

-0.24

TAM

-0.24

din

-0.24

aming

-0.24

estion

-0.24

ista

-0.24

æĢ¥æķĳ

-0.24

POSITIVE LOGITS

 Shades

0.27

 PhoneNumber

0.26

 Outputs

0.26

åĩºåı£

0.26

éĥ½ä¸įæķ¢

0.25

çĿĢåĬĽ

0.25

 outputs

0.25

OrNull

0.24

Outputs

0.24

undra

0.24

Activations Density 0.065%

to

No Comments

No Known Activations