INDEX

Explanations

except

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

çĦ¶èĢĮ

-0.28

ä½Ĩæĺ¯æĪĳ

-0.28

ä½Ĩæĺ¯ä»ĸ

-0.28

ä½Ĩå¥¹

-0.27

 HOWEVER

-0.27

ä½Ĩä»ĸ

-0.27

aticon

-0.26

ãģĦãģ¾ãģĻãģĮ

-0.26

aset

-0.26

ä½ĨæĪĳ

-0.26

POSITIVE LOGITS

 everything

0.34

all

0.34

 they

0.32

 every

0.32

å®ĥä»¬

0.31

every

0.29

 none

0.29

Ð»Ð°Ð½

0.28

all

0.28

ÑĢÑı

0.27

Activations Density 0.042%

except

No Comments

No Known Activations