© 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. 15457
    Prev
    Next
    INDEX
    Explanations

    say silk

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

    No Comments

    Negative Logits
     Stokes
    -17.88
    FLOAT
    -17.63
    \r
    -17.00
    侦查
    -16.50
     Klopp
    -16.38
    ลอย
    -16.13
    �
    -16.13
    _vect
    -16.00
    truck
    -15.81
     Travis
    -15.75
    POSITIVE LOGITS
    蚕
    22.50
    丝绸
    21.63
    桑
    18.88
     silk
    17.88
     sil
    16.75
     coco
    16.63
    _san
    16.25
    萱
    16.13
     Cater
    15.75
     SIL
    15.56
    Activations Density 0.063%

    No Known Activations