© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1744
    Prev
    Next
    INDEX
    Explanations

    author

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

    No Comments

    Negative Logits
    ANCH
    -17.13
    _FEED
    -16.75
    Eng
    -16.50
    _cc
    -15.69
     anchor
    -15.56
     angular
    -15.56
     angl
    -15.19
     feeding
    -15.06
    angen
    -15.06
    Creative
    -15.00
    POSITIVE LOGITS
    计算
    20.75
    wine
    19.50
     Battlefield
    18.75
     COMPUT
    17.88
     Romans
    17.88
     Gunn
    17.75
     Columbus
    17.63
    Comput
    17.38
     alcohol
    17.13
     computing
    17.13
    Activations Density 0.550%

    No Known Activations