INDEX

Explanations

after

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æ¸Ĺ

-0.31

cow

-0.27

way

-0.27

çļĦåģļæ³ķ

-0.27

åªĴ

-0.26

pir

-0.25

å©Ĩ

-0.25

æĭĽ

-0.25

 Rift

-0.25

 Batt

-0.25

POSITIVE LOGITS

adian

0.27

idor

0.26

 adulte

0.25

adult

0.24

ieurs

0.24

opsy

0.24

 hairs

0.24

gabe

0.24

ashi

0.23

 stimulation

0.23

Activations Density 0.024%

after

No Comments

No Known Activations