INDEX

Explanations

either

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

 Motorola

-0.29

åıĳåĩº

-0.27

ä¾§

-0.27

å®ł

-0.26

ë§¨

-0.26

Emm

-0.26

META

-0.25

(man

-0.25

Ð¾Ð²Ð¾

-0.25

çĶ·æĢ§

-0.25

POSITIVE LOGITS

ibre

0.27

åı¯æĥľ

0.27

-INF

0.27

 realised

0.26

 smarter

0.25

navbarSupportedContent

0.25

åı¸æ³ķ

0.25

ilestone

0.25

gil

0.25

 specialised

0.24

Activations Density 0.020%

either

No Comments

No Known Activations