© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14709
    Prev
    Next
    INDEX
    Explanations

    [Received:] => [Received:]

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

    No Comments

    Negative Logits
    latable
    -19.63
    kus
    -19.00
    iant
    -18.50
    hoot
    -18.13
    iesta
    -17.63
    깃
    -17.63
    лит
    -17.25
     CIT
    -17.13
    eus
    -16.88
    (Art
    -16.75
    POSITIVE LOGITS
     conform
    16.88
     Tor
    15.31
     terr
    14.75
     ano
    14.38
     Terr
    14.38
     underscore
    14.06
    Reg
    13.81
     Tape
    13.75
     Trace
    13.69
    康
    13.44
    Activations Density 0.079%

    No Known Activations