INDEX

Explanations

arguments, opinions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 à¹Ĩ

-0.28

ÑĮÐµÑĢ

-0.27

æĢ¥äºİ

-0.26

ä½Ĩä»ĸä»¬

-0.26

templ

-0.25

vor

-0.25

èĢĮæĺ¯

-0.25

aland

-0.24

èĦ±

-0.24

ised

-0.24

POSITIVE LOGITS

æ³Ĭ

0.28

 Harding

0.27

 externally

0.25

ft

0.24

 Applied

0.24

æĶ¿æ³ķ

0.24

umo

0.23

 judging

0.23

ãģĦãģĳ

0.23

 Thai

0.23

Activations Density 23.357%

arguments, opinions

No Comments

No Known Activations