INDEX

Explanations

,

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

ç¼ºåı£

-0.28

è¿¹

-0.28

rance

-0.27

ç¹ģèį£

-0.26

odb

-0.26

æ±Ĥ

-0.26

odef

-0.25

divider

-0.25

cation

-0.25

.orientation

-0.24

POSITIVE LOGITS

æľīçĶ¨çļĦ

0.28

 cooked

0.26

æıī

0.26

cooked

0.25

cmds

0.25

è¡¨æī¬

0.24

åħ«åįģ

0.24

heat

0.24

 flotation

0.23

æĮģæľīçļĦ

0.23

Activations Density 0.001%

,

No Comments

No Known Activations