INDEX

Explanations

new

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

åİŁåĽł

-0.28

äº§åĵģçļĦ

-0.26

 reason

-0.25

-wow

-0.25

bane

-0.24

 Burns

-0.24

reason

-0.24

é«¯

-0.24

ç¿ħ

-0.24

 curt

-0.24

POSITIVE LOGITS

lice

0.29

 mess

0.28

phis

0.27

UDA

0.27

.mvp

0.26

\t

0.26

 premises

0.25

vir

0.24

èİ«

0.24

ãĤģ

0.23

Activations Density 0.016%

new

No Comments

No Known Activations