INDEX

Explanations

here

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

ç©º

-0.26

 acre

-0.25

åľ°éľĩ

-0.25

sse

-0.25

éĺ³

-0.24

 EventEmitter

-0.24

 bore

-0.24

 drilled

-0.24

å°¹

-0.23

 complementary

-0.23

POSITIVE LOGITS

deaux

0.32

leasing

0.29

umblr

0.26

 nonatomic

0.26

POOL

0.24

 Malay

0.24

ugal

0.24

 Weiner

0.23

Ã¡ticas

0.23

è¡¡

0.23

Activations Density 0.008%

here

No Comments

No Known Activations