INDEX

Explanations

versa

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

 coat

-0.29

 reversed

-0.28

 kind

-0.27

demo

-0.26

Kind

-0.26

 demo

-0.25

-schema

-0.25

 sort

-0.25

LO

-0.25

æĪĲç«ĭäºİ

-0.25

POSITIVE LOGITS

itag

0.26

riteria

0.26

ktop

0.24

egment

0.24

 pager

0.24

ocket

0.24

SEG

0.24

ä¸Ģä¸ªæĺŁæľŁ

0.24

åı¯æĥ³

0.24

 Glyph

0.24

Activations Density 0.100%

versa

No Comments

No Known Activations