© 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. 14455
    Prev
    Next
    INDEX
    Explanations

    Ap

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

    No Comments

    Negative Logits
    雒
    -19.63
    Cro
    -19.38
     Adri
    -19.25
    榆
    -18.63
    皇
    -18.63
     Cro
    -18.13
    江东
    -17.75
    阆
    -17.75
    .bridge
    -17.75
     cro
    -17.75
    POSITIVE LOGITS
     Gins
    16.63
     desn
    16.63
    mods
    16.13
     Alma
    16.00
     Associates
    16.00
    _spot
    16.00
     naked
    15.75
    consin
    15.13
    hus
    14.75
    bers
    14.69
    Activations Density 1.303%

    No Known Activations