INDEX

Explanations

data/evidence

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

ä¼ļè®©ä½ł

-0.26

her

-0.26

 somehow

-0.25

è®©æĤ¨

-0.25

è´¢å¯Į

-0.24

erald

-0.24

cyl

-0.24

 woke

-0.24

ä½łä¹Ł

-0.24

her

-0.23

POSITIVE LOGITS

éĻĲãĤĬ

0.26

ç«Ń

0.25

RequiredMixin

0.25

MATCH

0.24

å¤§éģĵ

0.24

pedia

0.24

 ValidationResult

0.23

thÃ¨que

0.23

 Largest

0.23

Ø±ØŃ

0.23

Activations Density 0.010%

data/evidence

No Comments

No Known Activations