INDEX

Explanations

code, technical documents

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

ãĢĤãĢĮ

-0.27

 untranslated

-0.27

Â«

-0.25

åįĸåĩº

-0.24

åĵģ

-0.24

 Â«

-0.24

 Schumer

-0.23

CU

-0.23

åĭĭ

-0.23

 branches

-0.23

POSITIVE LOGITS

å¼Ī

0.25

scious

0.25

èŀ½

0.25

ween

0.24

 pylint

0.24

CEED

0.24

DidLoad

0.24

èµĶ

0.24

arily

0.23

å°ĳæķ°

0.23

Activations Density 4.778%

code, technical documents

No Comments

No Known Activations