INDEX

Explanations

p

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

ROID

-0.28

Åĺ

-0.26

niest

-0.26

 intox

-0.25

.isLoggedIn

-0.25

ç¿ħèĨĢ

-0.25

isLoggedIn

-0.25

apos

-0.25

åħ¥çĿ¡

-0.25

æľªæĪĲå¹´

-0.25

POSITIVE LOGITS

iments

0.30

ç¾ĬèĤī

0.27

ufs

0.27

rift

0.26

igan

0.26

çĪ½

0.25

ring

0.25

å¿½

0.25

 ring

0.24

cont

0.24

Activations Density 0.051%

p

No Comments

No Known Activations