INDEX

Explanations

academic research

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

æĪı

-0.29

ä¸Ģæīĭ

-0.27

adder

-0.27

/operator

-0.25

åįĬ

-0.25

ä¸ĢåįĬ

-0.24

 HALF

-0.23

 Interr

-0.23

 deeply

-0.23

.rm

-0.23

POSITIVE LOGITS

æĦ¿

0.27

 accom

0.26

forth

0.25

æ²§

0.24

zym

0.24

æĿĤ

0.24

 nÃło

0.24

 fait

0.24

laughter

0.23

 waiver

0.23

Activations Density 0.032%

academic research

No Comments

No Known Activations