INDEX

Explanations

Pleasant

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

ç®Ģä¾¿

-0.32

æł¸

-0.28

 coun

-0.26

çģ°

-0.26

IU

-0.25

arsed

-0.24

lauf

-0.24

çĤ³

-0.24

jab

-0.23

æİĮ

-0.23

POSITIVE LOGITS

åĿĢ

0.31

 hotter

0.26

è¶Ĭæĺ¯

0.26

ody

0.26

ewe

0.26

/MPL

0.25

-decoration

0.25

sar

0.25

decorators

0.25

ONY

0.24

Activations Density 0.000%

Pleasant

No Comments

No Known Activations