INDEX

Explanations

ella

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.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

dsl

-0.28

åģļåĪ°

-0.26

rit

-0.26

åľĪ

-0.26

-install

-0.26

åģļå¥½

-0.24

rip

-0.24

 ciÄħ

-0.24

stp

-0.24

 effectively

-0.24

POSITIVE LOGITS

UnderTest

0.27

uede

0.27

æ²¡æĥ³åĪ°

0.25

 Ð·Ð°Ñı

0.25

Beginning

0.25

 Gems

0.25

annel

0.24

 presum

0.24

 bureaucracy

0.24

èĴ¸åıĳ

0.23

Activations Density 37.820%

ella

No Comments

No Known Activations