INDEX

Explanations

Contrasting ideas/comparisons

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

 PLATFORM

-0.26

åħī

-0.25

èĩªæ²»åĮº

-0.25

 majority

-0.24

ORIA

-0.24

æĶ¯åĩº

-0.24

wick

-0.23

DeV

-0.23

Ĥ

-0.23

ToFit

-0.23

POSITIVE LOGITS

åı¦ä¸Ģ

0.48

 another

0.41

 others

0.39

others

0.39

åĪ«çļĦ

0.38

åħ¶ä»ĸçļĦ

0.38

åı¦ä¸Ģä¸ª

0.38

another

0.37

 Ð´ÑĢÑĥÐ³Ð¾Ð¹

0.36

 other

0.35

Activations Density 0.002%

Contrasting ideas/comparisons

No Comments

No Known Activations