INDEX

Explanations

Thai

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 rent

-0.29

aff

-0.28

 processed

-0.27

cre

-0.27

BuilderInterface

-0.26

 automatically

-0.26

 harvested

-0.26

åħ³åı£

-0.25

Reject

-0.25

aff

-0.25

POSITIVE LOGITS

ðŁĺĦ

0.30

æīĵåĵį

0.26

dru

0.25

:hidden

0.25

Reviewed

0.24

vro

0.24

åıĳæī¬

0.24

ograf

0.24

æıļ

0.24

iterr

0.24

Activations Density 0.008%

Thai

No Comments

No Known Activations