INDEX

Explanations

sentence components

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GP

-0.29

å¯»æī¾

-0.28

åĽ½äºº

-0.27

erset

-0.25

 tele

-0.25

æ¯ĴæĢ§

-0.25

 ethnic

-0.25

æİ¥åľ°æ°Ķ

-0.25

anje

-0.24

 ethnicity

-0.24

POSITIVE LOGITS

åħ¶æ¬¡æĺ¯

0.27

ynchronization

0.26

 Acting

0.25

axy

0.25

greens

0.24

/welcome

0.24

idebar

0.24

inya

0.24

 proofs

0.23

elage

0.23

Activations Density 9.979%

sentence components

No Comments

No Known Activations