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

    Neuronpedia

    Jacobian LensNEW
    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. 15211
    Prev
    Next
    INDEX
    Explanations

    say 0

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

    No Comments

    Negative Logits
    enet
    -17.88
    eder
    -17.63
    urg
    -17.50
    Chicago
    -17.25
    ug
    -16.38
    riding
    -16.25
    ugal
    -16.13
    gend
    -16.00
    盘
    -15.94
    gid
    -15.75
    POSITIVE LOGITS
    [__
    17.13
     captive
    14.06
     sta
    13.63
    ooks
    13.56
    .ST
    13.50
     zk
    13.44
     qualify
    13.44
    sta
    13.38
    ZW
    13.38
     branches
    13.19
    Activations Density 0.085%

    No Known Activations