INDEX

Explanations

dates

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

éĴĹ

-0.29

æ³Ħ

-0.26

ãĢĤ↵↵

-0.26

 histÃ³rico

-0.26

.";↵↵

-0.26

]=>

-0.26

æ³»

-0.25

mysqli

-0.25

.';↵

-0.25

åıįæŃ£

-0.25

POSITIVE LOGITS

elon

0.31

ä¿Ĥ

0.27

 Playboy

0.26

 Durant

0.26

.viewer

0.26

–

0.25

dur

0.24

 Major

0.24

 Snowden

0.24

inton

0.24

Activations Density 0.006%

dates

No Comments

No Known Activations