INDEX

Explanations

question words

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

ç´§åĩĳ

-0.28

annon

-0.26

ly

-0.26

åĲİ

-0.25

ansa

-0.24

hold

-0.24

ä¸´

-0.24

FD

-0.24

asking

-0.24

 standoff

-0.24

POSITIVE LOGITS

staff

0.28

ventions

0.25

æĹ¶éĹ´åĴĮ

0.25

Staff

0.25

vez

0.24

 Staff

0.24

ACTIVE

0.23

 staffers

0.23

riter

0.23

OUND

0.23

Activations Density 0.012%

question words

No Comments

No Known Activations