INDEX

Explanations

1

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

 Capitals

-0.28

 RequestContext

-0.26

inated

-0.25

dÃ¬

-0.25

ervised

-0.24

.digital

-0.24

áº¡ng

-0.24

INUE

-0.24

 NDEBUG

-0.24

.chrome

-0.24

POSITIVE LOGITS

JC

0.28

tem

0.28

 Affero

0.26

@test

0.25

éĤ£è¾¹

0.24

 derives

0.24

åĪłéĻ¤æĪĲåĬŁ

0.24

PGA

0.24

 nowadays

0.23

æĬ¤èº«ç¬¦

0.23

Activations Density 0.002%

1

No Comments

No Known Activations