INDEX

Explanations

adaptability

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

Ñİ

-0.28

é¢¦

-0.28

å°¾

-0.28

 tails

-0.26

GEST

-0.24

ges

-0.24

è«¸

-0.24

TD

-0.24

aju

-0.24

.schedulers

-0.24

POSITIVE LOGITS

çŃĶåį·

0.28

æıĲéĨĴ

0.27

startIndex

0.26

ampaign

0.26

ucker

0.26

acute

0.25

InBackground

0.25

asin

0.24

\Migration

0.24

 startIndex

0.24

Activations Density 0.006%

adaptability

No Comments

No Known Activations