INDEX

Explanations

sub

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

inesis

-0.31

ciÃ³n

-0.29

ylon

-0.28

ç»ĨåĪĨ

-0.27

zen

-0.27

äºļæ´²

-0.25

 pageTitle

-0.25

äºļ

-0.25

atically

-0.25

ces

-0.24

POSITIVE LOGITS

ambil

0.27

Ð°Ñħ

0.27

ç¤¾

0.26

 freaking

0.26

 translators

0.25

atching

0.25

agram

0.25

 unre

0.25

åı£

0.24

 enchanted

0.24

Activations Density 0.033%

sub

No Comments

No Known Activations