© 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. 14414
    Prev
    Next
    INDEX
    Explanations

    im_start

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

    No Comments

    Negative Logits
    oma
    -18.88
    wan
    -16.25
    uran
    -15.56
    usan
    -14.56
    vement
    -14.50
    는데
    -14.38
    ua
    -14.25
    WI
    -14.19
    omas
    -14.13
    emon
    -14.06
    POSITIVE LOGITS
     LTC
    16.38
    .Framework
    16.25
    لك
    15.81
    .lt
    15.25
    .zz
    15.06
    lz
    14.81
    lk
    14.81
     Lak
    14.69
    ieri
    14.69
     loud
    14.56
    Activations Density 0.014%

    No Known Activations