INDEX

Explanations

than

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 usually

-0.43

usually

-0.42

éĢļå¸¸

-0.41

 typically

-0.41

 Usually

-0.40

éĢļå¸¸æĺ¯

-0.40

Usually

-0.37

 Ð¾Ð±ÑĭÑĩÐ½Ð¾

-0.37

 Typically

-0.37

typically

-0.36

POSITIVE LOGITS

any

0.29

in

0.29

ANY

0.27

çŀ½

0.27

 during

0.27

 domains

0.27

åľ¨ä¸Ĭæµ·

0.26

èĩªç§ģ

0.26

 convergence

0.26

çĶµéĺ»

0.26

Activations Density 0.001%

than

No Comments

No Known Activations