INDEX

Explanations

+

np_max-act · gemini-2.0-flash

numeric quantities expressed with a trailing plus sign to indicate “or more” amounts.

oai_token-act-pair · gpt-5 Triggered by @liuliujiujiu05

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 limit

-0.27

âģ½

-0.27

 competit

-0.25

çķ¹

-0.25

vers

-0.25

ä¸¥

-0.25

å®¹

-0.25

ç»ıè¿ĩ

-0.25

åĲ¬ä¼Ĺ

-0.24

Vs

-0.24

POSITIVE LOGITS

Raised

0.28

 Stir

0.27

*</

0.25

Ïĭ

0.24

DataFrame

0.24

icable

0.24

åĬ¼

0.24

ä¸Ģåº§

0.24

Toggle

0.23

 Toggle

0.23

Activations Density 0.003%

+

numeric quantities expressed with a trailing plus sign to indicate “or more” amounts.

No Comments

No Known Activations