© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15644
    Prev
    Next
    INDEX
    Explanations

    say encryption

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Burl
    -17.50
    血液
    -17.38
    噘
    -17.25
     Spokane
    -17.13
    收购
    -16.38
    blood
    -16.00
     Harvest
    -15.94
     máu
    -15.94
     Toll
    -15.56
    ItemImage
    -15.50
    POSITIVE LOGITS
    加密
    43.75
     encryption
    42.75
     encrypt
    40.25
     encrypted
    39.50
    Encryption
    38.00
    crypt
    37.75
     Encryption
    37.75
    Encrypt
    37.50
    Crypt
    37.25
     decryption
    37.25
    Activations Density 0.233%

    No Known Activations