INDEX

Explanations

ine

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

erty

-0.28

å¤ªç©º

-0.27

éĩĮ

-0.27

ogs

-0.26

ypo

-0.25

ulty

-0.25

ussen

-0.25

 chÃ¢n

-0.25

truth

-0.25

 ----------------------------------------------------------------------------------------------------------------

-0.25

POSITIVE LOGITS

 refuses

0.27

 acet

0.26

äºĮåįģå¹´

0.26

åįģäºĶæĿ¡

0.26

çķĭ

0.25

-suite

0.25

 dreamed

0.25

 Ð´Ð¸Ð°Ð³Ð½Ð¾ÑģÑĤ

0.25

å¾Ĺä¸įåĪ°

0.25

å¡µ

0.24

Activations Density 0.002%

ine

No Comments

No Known Activations