INDEX

Explanations

initial

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

's

-0.27

 Changing

-0.25

ternal

-0.25

éĺ²æŃ¢

-0.25

 prevents

-0.24

ä¸Ģå¦ĤæĹ¢å¾Ģ

-0.24

åľ°çľĭçĿĢ

-0.24

 Increasing

-0.24

 Spare

-0.24

POSITIVE LOGITS

 registrations

0.33

 stages

0.30

BOSE

0.29

 installations

0.29

 gatherings

0.28

éĺ¶æ®µ

0.27

ãĥ¥ãĥ¼

0.27

 investigations

0.27

 instal

0.27

 invasion

0.26

Activations Density 0.802%

initial

No Comments

No Known Activations