INDEX

Explanations

Code and "Columbia" references

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

ants

-0.29

ider

-0.28

çľ¯

-0.28

Ð°ÑĢÑĮ

-0.25

-save

-0.25

çĬĩ

-0.25

æ¾³

-0.25

ees

-0.24

åį¿

-0.24

è·ĳ

-0.24

POSITIVE LOGITS

à¤¢

0.28

pell

0.26

å®«å»·

0.25

utsche

0.25

éĴ¢

0.25

 Steel

0.25

æīĵäºĨ

0.24

 cityName

0.24

PackageName

0.24

å£°æĺİ

0.24

Activations Density 0.004%

Code and "Columbia" references

No Comments

No Known Activations