INDEX

Explanations

ip

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

çł°

-0.28

è·¯åı£

-0.27

åĿĲä¸ĭ

-0.27

WH

-0.27

lie

-0.26

 benches

-0.26

æ²¿æµ·

-0.25

éĺ¡

-0.25

WH

-0.25

uhan

-0.25

POSITIVE LOGITS

endale

0.28

ç¿®

0.26

åĽ°

0.25

çĶ¨äºº

0.25

dbname

0.25

 STRICT

0.24

çĸı

0.24

å¹²éĥ¨éĺŁä¼į

0.24

 activ

0.24

dde

0.24

Activations Density 0.006%

ip

No Comments

No Known Activations