INDEX

Explanations

Internet questions and answers

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

å¼Ľ

-0.25

alten

-0.25

ÅĽl

-0.25

ãĤ±

-0.25

 Treatment

-0.24

marks

-0.24

é»Ħéĩĳ

-0.24

acc

-0.24

èµİ

-0.24

.acc

-0.24

POSITIVE LOGITS

)[-

0.28

Ster

0.28

 buggy

0.26

bh

0.26

ä¸Ńåħ±

0.26

æĶ¯çĲĥéĺŁ

0.26

ä¸ĢåıĮ

0.26

éĽĩ

0.25

 unidentified

0.25

ä½ĵèĤ²åľº

0.24

Activations Density 0.010%

Internet questions and answers

No Comments

No Known Activations