INDEX

Explanations

result

np_max-act · gemini-2.0-flash

references to outcomes or findings—mentions of the result of an action, experiment, query, or study.

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

åķ¬

-0.27

ç«ĭãģ¡

-0.26

à¹ģà¸Ķà¸Ļ

-0.25

ammable

-0.24

owl

-0.24

è¿©

-0.24

uity

-0.24

Ð·Ð´

-0.24

MetaData

-0.24

æĮ¡

-0.24

POSITIVE LOGITS

symbol

0.26

ç»ĵ

0.25

cbd

0.25

-symbol

0.25

corn

0.25

pdo

0.25

 symbolism

0.25

 Symbol

0.24

 symbol

0.24

åĵªå®¶

0.24

Activations Density 0.002%

result

references to outcomes or findings—mentions of the result of an action, experiment, query, or study.

No Comments

No Known Activations