INDEX

Explanations

last

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

Ð¸Ð½Ñĭ

-0.26

çľ©

-0.26

prit

-0.25

æľīæĦı

-0.25

Ler

-0.24

æłĩé¢ĺ

-0.24

åıįé¦Ī

-0.24

bral

-0.24

 brightness

-0.24

 surre

-0.23

POSITIVE LOGITS

 unique

0.27

 Fargo

0.27

 Perm

0.26

Perm

0.26

.unique

0.25

æľĶ

0.24

RuleContext

0.24

çł§

0.24

éºŁ

0.24

 uniqu

0.24

Activations Density 0.006%

last

No Comments

No Known Activations