INDEX

Explanations

2

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

<![

-0.27

 conflic

-0.26

fter

-0.25

oust

-0.24

possible

-0.24

ilingual

-0.24

 Ð³Ð¾Ð»Ð¾Ñģ

-0.24

 hÃ¨

-0.24

 tails

-0.24

 scrolled

-0.24

POSITIVE LOGITS

å¾Ĺèµ·

0.35

allel

0.28

è½¦åºĵ

0.26

 Pear

0.26

://"

0.25

tering

0.25

locking

0.25

raison

0.24

 Locked

0.24

åĽŃ

0.24

Activations Density 0.002%

2

No Comments

No Known Activations