INDEX

Explanations

forgiveness/explanations

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

è¿Ľåĩº

-0.27

ØªØ±

-0.27

bang

-0.27

orp

-0.26

ernes

-0.25

adan

-0.24

Bi

-0.24

ual

-0.24

Äĥng

-0.24

igen

-0.24

POSITIVE LOGITS

stdClass

0.30

occus

0.30

atÃ³

0.26

ë¡Ŀ

0.26

<<

0.26

/disc

0.25

ayar

0.24

 <<↵

0.23

NXT

0.23

 devote

0.23

Activations Density 0.003%

forgiveness/explanations

No Comments

No Known Activations