INDEX

Explanations

Names/Locations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.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

blink

-0.28

igrations

-0.26

èĬ·

-0.26

 coin

-0.25

å¼Ģå±ķ

-0.24

ulin

-0.24

 formation

-0.24

 skeletons

-0.24

formation

-0.24

 Just

-0.24

POSITIVE LOGITS

å°½å¤´

0.26

 insiders

0.25

 Ð±Ð»Ð°Ð³Ð¾Ð´Ð°ÑĢÑı

0.24

 Arena

0.24

igned

0.24

çļĦç¡®

0.23

çł´ç¢İ

0.23

 Ð²ÑģÑĤÑĢÐµÑĩÐ°

0.23

ieder

0.23

èĩªçĦ¶çģ¾å®³

0.23

Activations Density 5.435%

Names/Locations

No Comments

No Known Activations