INDEX

Explanations

actually

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ual

-0.27

 negatives

-0.27

 ment

-0.27

 excell

-0.26

æµª

-0.25

åį¬

-0.25

è´Ł

-0.25

Ø¡

-0.24

 Ð¿ÑĢÐ¸Ð½

-0.24

 bÃ¶

-0.24

POSITIVE LOGITS

Ľå»º

0.30

aab

0.26

çļĦåľ°

0.25

ROLS

0.25

æĸĭ

0.25

vara

0.24

resher

0.24

ocab

0.24

dra

0.23

à¸²à¸ģ

0.23

Activations Density 0.216%

actually

No Comments

No Known Activations