INDEX

Explanations

policy

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

è·Į

-0.31

Kn

-0.27

 bern

-0.26

æ²¡éĶĻ

-0.26

kn

-0.25

 Drops

-0.24

ixin

-0.24

ìłĪ

-0.23

åĲĥ

-0.23

Fe

-0.23

POSITIVE LOGITS

/animations

0.28

 McInt

0.28

*__

0.27

buie

0.26

åį«åģ¥

0.25

{o

0.25

èĬ¹

0.24

croll

0.23

 reelection

0.23

åı£

0.23

Activations Density 0.001%

policy

No Comments

No Known Activations