INDEX

Explanations

statistics

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

IFE

-0.31

erk

-0.27

 åķĨåĵģ

-0.27

åŁĴ

-0.26

)init

-0.25

 Merch

-0.25

emm

-0.25

åĪº

-0.25

cue

-0.25

Merchant

-0.25

POSITIVE LOGITS

å¦¥

0.29

çļĦæ¦Ĥçİĩ

0.27

 Parm

0.26

æ¦Ĥçİĩ

0.26

 survives

0.26

probability

0.26

Parm

0.26

Histogram

0.25

semi

0.25

 probability

0.25

Activations Density 0.013%

statistics

No Comments

No Known Activations