INDEX

Explanations

Angel

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å²ģæľĪ

-0.30

ÑĢÑĥÑĩ

-0.25

elon

-0.25

Ð³Ð»ÑıÐ´

-0.25

 Bros

-0.25

ÑĢÑĥ

-0.25

_pas

-0.24

ideon

-0.24

.nz

-0.24

åĨ²åĩ»

-0.24

POSITIVE LOGITS

bane

0.29

nox

0.27

 analyzes

0.25

rÃ´

0.25

åĻª

0.25

tracks

0.25

SystemService

0.24

rowse

0.23

è½¸

0.23

 accomplished

0.23

Activations Density 0.003%

Angel

No Comments

No Known Activations