INDEX

Explanations

conditionals

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

rang

-0.27

uml

-0.27

ÑĩÐ¸Ð²

-0.27

ugin

-0.26

ava

-0.26

GAP

-0.26

-gap

-0.26

éļĻ

-0.25

ake

-0.25

eric

-0.25

POSITIVE LOGITS

è¿ĲåĬ¿

0.27

<![

0.26

 moth

0.26

.sy

0.25

 sympathy

0.25

 reim

0.25

 LoginForm

0.25

 watched

0.25

ris

0.25

idget

0.24

Activations Density 0.023%

conditionals

No Comments

No Known Activations