INDEX

Explanations

terror/terrorism

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

tÃŃ

-0.28

.override

-0.26

incer

-0.24

 approximate

-0.23

 Pant

-0.23

èĹĲ

-0.23

æĸ¹è¨Ģ

-0.23

ä¹ĭä¸Ń

-0.23

ew

-0.23

velope

-0.23

POSITIVE LOGITS

åĩłçİĩ

0.28

Occ

0.26

opal

0.26

 borderBottom

0.25

.Thread

0.25

args

0.24

=back

0.24

argc

0.24

Tac

0.24

 Street

0.23

Activations Density 0.787%

terror/terrorism

No Comments

No Known Activations