INDEX

Explanations

work

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ers

-1.57

ERS

-0.82

ersen

-0.56

ersh

-0.47

èĢħçļĦ

-0.46

ered

-0.44

er

-0.43

erset

-0.43

æ³¨æĦı

-0.41

èĢħ

-0.41

POSITIVE LOGITS

 disemb

0.28

ç£ĭ

0.28

entionPolicy

0.25

ä¸įçĲĨ

0.25

es

0.25

ä¸įå¹³è¡¡

0.25

iendo

0.24

ä¸įç»ıæĦı

0.24

å®Ŀ

0.24

ighth

0.24

Activations Density 0.023%

work

No Comments

No Known Activations