INDEX

Explanations

polymer

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

 Plain

-0.34

Plain

-0.30

emann

-0.29

Straight

-0.28

 Straight

-0.28

 straightforward

-0.27

åĲĪéĩĳ

-0.27

å°ĳæķ°æ°ĳæĹı

-0.26

em

-0.26

subclass

-0.26

POSITIVE LOGITS

 sher

0.33

æĪ·å¤ĸ

0.28

è¯ķè¯ķ

0.27

èĲ¥åĪ©

0.26

 downs

0.26

 prospect

0.26

ä¸įèĩ³äºİ

0.26

 outdoors

0.26

eration

0.25

 HACK

0.25

Activations Density 0.009%

polymer

No Comments

No Known Activations