INDEX

Explanations

technical language

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

ç§¯ç´¯

-0.30

ç´¯

-0.28

iten

-0.28

 accumulate

-0.27

çİĦ

-0.26

ç´¯ç§¯

-0.26

 accumulator

-0.26

 Accum

-0.25

Cru

-0.25

ums

-0.24

POSITIVE LOGITS

PROP

0.29

isson

0.28

åĪ°è¿ĻéĩĮ

0.25

 componentWill

0.25

 prop

0.25

oine

0.24

 pers

0.24

-offs

0.23

æı

0.23

 repmat

0.23

Activations Density 0.023%

technical language

No Comments

No Known Activations