INDEX

Explanations

varied text sources

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_9.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.9.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç»¯

-0.28

åĪĨéħį

-0.28

æĿī

-0.27

åĬ±

-0.26

 available

-0.25

à¸Īà¸³

-0.24

è·¯åĨµ

-0.24

 traff

-0.24

 amen

-0.24

æĹłåģ¿

-0.24

POSITIVE LOGITS

-board

0.28

PED

0.28

-clock

0.28

æĤĿ

0.26

*__

0.26

çģ¯

0.26

ç»Ħç»ĩé¢Ĩå¯¼

0.26

iddles

0.26

è¯ķçĤ¹å·¥ä½ľ

0.25

Jos

0.25

Activations Density 0.919%

varied text sources

No Comments

No Known Activations