INDEX

Explanations

code and copyright notices

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

eries

-0.28

.jav

-0.26

 Conspiracy

-0.25

_Static

-0.24

olatile

-0.24

acey

-0.24

ilia

-0.24

isco

-0.23

autiful

-0.23

à¸§à¸¥

-0.23

POSITIVE LOGITS

_CM

0.33

otron

0.29

çĽ¸è§ģ

0.27

æİĪæĿĥ

0.26

>[]

0.26

odem

0.25

 mains

0.24

åĲŃ

0.24

_cm

0.24

ocale

0.24

Activations Density 0.010%

code and copyright notices

No Comments

No Known Activations