INDEX

Explanations

expressing positive sentiment

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

 Prefer

-0.26

flex

-0.25

ci

-0.24

ä¸ĢèĪ¬éĥ½æĺ¯

-0.24

atform

-0.24

Dear

-0.24

 grips

-0.24

 flex

-0.24

 preferably

-0.23

å±±åºĦ

-0.23

POSITIVE LOGITS

ç§°

0.39

ç§°ä¹ĭä¸º

0.36

ç¨±

0.33

 nothing

0.31

åı«

0.31

ç§°ä¹ĭ

0.29

ä¹ĭç§°

0.29

 called

0.29

.isNull

0.29

è¯©

0.28

Activations Density 0.006%

expressing positive sentiment

No Comments

No Known Activations