INDEX

Explanations

5

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

report

-0.27

Ta

-0.27

ä¼łç»ŁçļĦ

-0.27

Le

-0.27

 equivalent

-0.26

 dramatic

-0.26

åĪ¸

-0.25

å¤§çīĩ

-0.24

	report

-0.24

To

-0.24

POSITIVE LOGITS

 Setter

0.32

å¯¹ä»ĸä»¬

0.30

ãĢģ“

0.28

ancias

0.27

“↵↵

0.27

’↵↵

0.27

ForResource

0.26

è¦Ĩ

0.26

hte

0.25

atown

0.25

Activations Density 0.009%

5

No Comments

No Known Activations