INDEX

Explanations

atr

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 chore

-0.27

IVAL

-0.26

opal

-0.26

 danced

-0.25

novation

-0.25

oten

-0.24

èĻİ

-0.24

/Instruction

-0.23

ä¹ĭä½Ļ

-0.23

illes

-0.23

POSITIVE LOGITS

Contact

0.25

ariat

0.25

 Contact

0.25

è§¦åıĬ

0.25

ä¿±

0.24

éĤ£æ®µ

0.24

kim

0.24

Labour

0.24

Agents

0.24

æİ¥è§¦

0.24

Activations Density 0.004%

atr

No Comments

No Known Activations