INDEX

Explanations

most

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

 Jensen

-0.28

 stdClass

-0.26

åħĥ

-0.26

çļĦæľĭåıĭ

-0.26

ither

-0.25

-default

-0.25

 Citation

-0.24

 tháºŃp

-0.24

Ø¹ÙĬ

-0.24

 ListItem

-0.24

POSITIVE LOGITS

 patched

0.28

 soaked

0.28

onta

0.28

asca

0.27

æ³Ķ

0.26

quete

0.24

argin

0.24

apult

0.24

(Layout

0.24

çĺ«

0.24

Activations Density 0.041%

most

No Comments

No Known Activations