INDEX

Explanations

you

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

åıį

-0.29

 clos

-0.28

 lens

-0.28

æĹ¶åĪ»

-0.27

Fr

-0.26

ent

-0.26

Fra

-0.26

Fra

-0.25

dra

-0.25

 rust

-0.25

POSITIVE LOGITS

æĨ¾

0.30

ãģ¾ãģ¾

0.29

ctest

0.28

bery

0.28

åĨįçĶŁ

0.26

shal

0.25

ç½ĳç«Ļåľ°åĽ¾

0.24

fill

0.24

 destiny

0.24

 evac

0.24

Activations Density 0.012%

you

No Comments

No Known Activations