INDEX

Explanations

here

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

æľ¬æ¬¡æ´»åĬ¨

-0.31

æľīæĿ¡ä»¶

-0.28

 overs

-0.27

 electrom

-0.26

äºĨåĲĹ

-0.24

 basil

-0.24

 disp

-0.24

å¹¿å¤§ç¾¤ä¼Ĺ

-0.24

ennes

-0.24

åĪļæīį

-0.23

POSITIVE LOGITS

round

0.27

SourceType

0.26

jours

0.25

 onward

0.25

rounded

0.25

 Forever

0.25

 getResource

0.25

inate

0.25

ingo

0.24

æ¯ıéļĶ

0.24

Activations Density 0.020%

here

No Comments

No Known Activations