INDEX

Explanations

ia

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

atus

-0.28

atis

-0.27

ÑħÐ¾Ð´Ð¸Ð¼

-0.26

ropolitan

-0.26

)V

-0.24

icum

-0.24

ä»Ĭå¹´

-0.24

ignum

-0.23

 anno

-0.23

åħ«å¤§

-0.23

POSITIVE LOGITS

å·¥å§Ķ

0.29

éĮĦ

0.29

 Suggestions

0.28

Suggestions

0.26

dbe

0.26

èĿĩ

0.26

å£¯

0.26

 sibling

0.25

å½ķ

0.25

Extras

0.25

Activations Density 0.001%

ia

No Comments

No Known Activations