INDEX

Explanations

convolution

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zo

-0.27

oric

-0.27

 mood

-0.27

{'

-0.25

up

-0.25

roph

-0.25

ãģŀ

-0.24

åĬ³åĬ¨åĬĽ

-0.24

clus

-0.24

ÑĢÑĥ

-0.24

POSITIVE LOGITS

æªĲ

0.28

CommandEvent

0.27

adaptive

0.25

è½¦åĨħ

0.24

 faults

0.24

_hidden

0.24

åħ¨åĮº

0.24

 ÄĳÃ¡m

0.24

charset

0.24

 Aires

0.24

Activations Density 26.117%

convolution

No Comments

No Known Activations