INDEX

Explanations

ve

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çľĭä¸Ģçľĭ

-0.26

çĥ¹

-0.26

æīĢåľ¨

-0.25

çĽ¸åħ³ä¿¡æģ¯

-0.24

ppy

-0.24

åĻ¨å®ĺ

-0.24

çĪ±åĽ½ä¸»ä¹ī

-0.23

 sá»©c

-0.23

èĺħ

-0.23

 prÃ©

-0.23

POSITIVE LOGITS

éķľå¤´

0.28

ä»£

0.28

{:

0.26

iation

0.26

-translate

0.26

åº

0.25

 translate

0.25

Ð¸Ð¶

0.24

æ¬ł

0.24

 OnCollision

0.23

Activations Density 45.998%

ve

No Comments

No Known Activations