INDEX

Explanations

university

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

åħļåĴĮ

-0.27

¶Ī

-0.27

ocode

-0.26

å¸Ĥäººå¤§

-0.25

 consuming

-0.25

çĹ¿

-0.24

emacs

-0.24

çĽĽå¤§

-0.24

la

-0.24

æĸ¹æ¡Ī

-0.24

POSITIVE LOGITS

plies

0.26

ä»ħ

0.25

omat

0.24

 thirteen

0.23

Means

0.23

ation

0.23

owl

0.23

 Means

0.23

ATION

0.23

 Panc

0.23

Activations Density 0.001%

university

No Comments

No Known Activations