INDEX

Explanations

pair

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

è¦ģç´§

-0.31

otle

-0.28

RG

-0.26

moment

-0.26

æĹħè¡Į

-0.26

iture

-0.26

urt

-0.25

 Moment

-0.25

Moment

-0.25

æĬĬæīĭ

-0.25

POSITIVE LOGITS

åĮĸè§£

0.27

 aisle

0.27

ForObject

0.27

ocks

0.26

_overlap

0.25

eve

0.25

ingo

0.25

 sensible

0.24

ç¼ĺ

0.23

åĬ£åĬ¿

0.23

Activations Density 0.256%

pair

No Comments

No Known Activations