INDEX

Explanations

conversational text

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

æŀī

-0.30

Invariant

-0.28

egr

-0.28

egin

-0.27

rys

-0.26

aida

-0.26

.Invariant

-0.26

eto

-0.26

anged

-0.25

ald

-0.25

POSITIVE LOGITS

POSITION

0.27

 positional

0.27

spring

0.27

è¯´åĪ°

0.26

 exact

0.25

]'

0.25

ÙĤÙĩ

0.25

exact

0.25

ä¸įæĸŃåıĳå±ķ

0.25

çŁŃæľŁåĨħ

0.24

Activations Density 0.003%

conversational text

No Comments

No Known Activations