INDEX

Explanations

awards

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Autonomous

-0.27

annel

-0.26

çĭ¬ç«ĭ

-0.26

åįĩåĢ¼

-0.26

herits

-0.26

blr

-0.25

æľīä¿¡å¿ĥ

-0.24

<body

-0.24

-scripts

-0.24

onomous

-0.24

POSITIVE LOGITS

bog

0.28

yet

0.27

ãĤĪãģĨ

0.27

é¡¶

0.26

è¿ľ

0.26

IGH

0.26

hab

0.25

å¤§åĨĽ

0.25

 universal

0.25

Activations Density 0.059%

awards

No Comments

No Known Activations