© 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. 15667
    Prev
    Next
    INDEX
    Explanations

    fur

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

    No Comments

    Negative Logits
    饮酒
    -18.00
     balcony
    -17.63
    orc
    -17.13
    巩
    -16.88
    (student
    -16.88
    Student
    -16.50
    钋
    -16.50
    司机
    -16.38
    (Student
    -16.25
    odate
    -16.25
    POSITIVE LOGITS
    羊毛
    28.13
    毛
    26.13
     hairs
    23.63
     wool
    22.25
    绒
    21.75
     hair
    21.50
    fur
    21.13
     hairy
    20.50
     Hair
    19.50
     fur
    19.13
    Activations Density 0.126%

    No Known Activations