INDEX

Explanations

programming concepts

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

æĦıè¯Ĩ

-0.28

æ¶ĤæĬ¹

-0.26

wash

-0.25

bite

-0.25

Anonymous

-0.25

å¹²äºĭ

-0.24

 snapped

-0.24

ster

-0.24

onaut

-0.24

apo

-0.24

POSITIVE LOGITS

åĹ£

0.29

myModal

0.27

.sal

0.26

REAM

0.25

 congr

0.25

ersions

0.25

 Month

0.24

éĹ®ä»ĸ

0.24

 enjo

0.23

èµ°ä¸ĭåİ»

0.23

Activations Density 0.003%

programming concepts

No Comments

No Known Activations