INDEX

Explanations

the

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä»½

-0.29

pen

-0.28

æľªæĪĲå¹´

-0.27

ughter

-0.26

æľīä¸ª

-0.25

IMIT

-0.25

ç¼ĵåĨ²

-0.25

bon

-0.25

å½Ĵå±ŀ

-0.25

lemn

-0.25

POSITIVE LOGITS

evity

0.30

à¸£à¸ĵ

0.29

å·¥ä½ľä¼ļè®®

0.26

æĸ°æ¬¾

0.26

SessionFactory

0.25

 Advance

0.25

ieg

0.24

Ð¾Ð²Ð¸Ñĩ

0.24

Ã©rie

0.23

oluciÃ³n

0.23

Activations Density 0.000%

the

No Comments

No Known Activations