INDEX

Explanations

chatbot, coding mix

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

 ling

-0.28

 stag

-0.27

 otherwise

-0.26

åħ°

-0.25

too

-0.25

sit

-0.24

rec

-0.24

 scop

-0.24

tl

-0.24

ffe

-0.24

POSITIVE LOGITS

ä¼Ĭæĭī

0.30

çŃĶåį·

0.28

åī¯

0.27

ç»ĥä¹ł

0.27

.toJSON

0.26

Career

0.26

 subsystem

0.26

ÙĪÙħØ©

0.26

 Career

0.26

ÑĦÐ°

0.25

Activations Density 0.040%

chatbot, coding mix

No Comments

No Known Activations