© 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. 14537
    Prev
    Next
    INDEX
    Explanations

    say numbers

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

    No Comments

    Negative Logits
    杞
    -22.50
    シリ
    -22.50
    sut
    -19.88
    ambi
    -19.75
    rene
    -19.25
    顺德
    -18.88
    pire
    -18.50
     Sherlock
    -18.38
    ansible
    -18.38
    ammen
    -17.88
    POSITIVE LOGITS
     Eag
    16.38
     lag
    16.13
     Casc
    14.94
    ed
    14.94
    St
    14.56
    �
    14.56
    ov
    13.88
    lag
    13.81
    ag
    13.69
     Lav
    13.69
    Activations Density 0.064%

    No Known Activations