INDEX

Explanations

code errors

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

ueur

-0.31

timing

-0.30

rvine

-0.28

iÄĻ

-0.26

uru

-0.26

inha

-0.25

ä¸ĵå¿ĥ

-0.25

 pinch

-0.25

è½Ń

-0.25

 Timing

-0.24

POSITIVE LOGITS

åı·

0.28

Äĳ

0.27

èĻŁ

0.27

ä¸Ĭæľī

0.27

jure

0.26

empl

0.25

 cooperating

0.25

/GPL

0.25

à¹Ģà¸¢

0.25

 STDOUT

0.25

Activations Density 0.011%

code errors

No Comments

No Known Activations