INDEX

Explanations

as

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĸĩç«ł

-0.28

æķ´ä½ĵ

-0.26

 Cummings

-0.26

èº«ä½ĵ

-0.25

åŁĭ

-0.25

æ¯Ķè¾ĥå¤ļ

-0.25

 null

-0.24

 æķ

-0.24

æĸĻ

-0.24

ORY

-0.24

POSITIVE LOGITS

èĥľè´Ł

0.28

ccd

0.26

eneg

0.26

 STORAGE

0.26

orget

0.26

ingo

0.26

éī´å®ļ

0.26

 measurements

0.25

å¹³æĹ¶

0.25

SAN

0.25

Activations Density 0.002%

as

No Comments

No Known Activations