INDEX

Explanations

mechanics/engines

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

åŃ¦çĶŁä»¬

-0.31

 students

-0.30

 shel

-0.29

åŃ¦çĶŁ

-0.27

å¦¥

-0.27

å¯¹åŃ¦çĶŁ

-0.26

 alarmed

-0.26

landscape

-0.26

 landscape

-0.26

=pk

-0.25

POSITIVE LOGITS

 insensitive

0.30

bff

0.30

less

0.28

çŃļ

0.26

LESS

0.26

acid

0.26

éĩİ

0.26

emo

0.26

ãĥ¬ãĤ¹

0.25

æĥħåķĨ

0.25

Activations Density 0.018%

mechanics/engines

No Comments

No Known Activations