© 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. 14648
    Prev
    Next
    INDEX
    Explanations

    say 0 or 3

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

    No Comments

    Negative Logits
    壁
    -18.50
    hell
    -18.25
    esto
    -16.63
     hell
    -16.13
    hall
    -15.81
     Faul
    -14.69
     shit
    -14.44
    ment
    -14.31
     Ell
    -14.19
     sour
    -14.19
    POSITIVE LOGITS
     Eag
    16.38
    祺
    16.25
    奘
    15.06
     conditioner
    14.94
    ATEG
    14.94
    鳄
    14.94
    -pad
    14.81
    PropertyName
    14.81
     Lyon
    14.75
     Cavaliers
    14.69
    Activations Density 0.007%

    No Known Activations