INDEX

Explanations

allow

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åŁ

-0.28

 crawled

-0.27

erea

-0.26

Ø±Ø§Ø¡

-0.26

ability

-0.25

alers

-0.24

reas

-0.24

ç¤

-0.24

oss

-0.24

.Visual

-0.24

POSITIVE LOGITS

äº¤ä»ĺ

0.29

 Ã¡

0.26

äº¤æİ¥

0.24

äº¤

0.24

é¦¥

0.24

éĻ¤å¤ķ

0.23

.isNull

0.23

à¸ģà¸£à¸°à¹Ģà¸Ľ

0.23

 factor

0.23

-going

0.23

Activations Density 1.818%

allow

No Comments

No Known Activations