© 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. 14688
    Prev
    Next
    INDEX
    Explanations

    [<commit_before>] => [<commit_before>]

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

    No Comments

    Negative Logits
     ldb
    -20.00
    antom
    -18.88
    otton
    -18.13
    巴基
    -17.88
    aea
    -17.75
     Tanner
    -17.75
    abee
    -17.50
    acie
    -17.38
     nonatomic
    -16.88
    花开
    -16.63
    POSITIVE LOGITS
     Kling
    17.50
    Sch
    16.75
    SCP
    16.50
    rish
    16.50
    crit
    16.13
    歧视
    15.81
     Fri
    15.69
    スク
    15.69
    祁
    15.69
     scr
    15.56
    Activations Density 0.007%

    No Known Activations