© 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. 14616
    Prev
    Next
    INDEX
    Explanations

    [phrase] => the

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

    No Comments

    Negative Logits
    ubar
    -18.13
    obil
    -18.00
    plat
    -17.25
    iation
    -16.38
    oren
    -16.25
    啡
    -15.69
    edi
    -15.44
    angular
    -15.25
    pager
    -15.25
    eme
    -15.06
    POSITIVE LOGITS
     Creek
    14.94
    chner
    14.13
     Lane
    13.81
     Alec
    13.63
     Comp
    13.63
     Achilles
    13.06
    泉
    13.00
    Comp
    12.81
    æk
    12.81
    _comp
    12.69
    Activations Density 0.023%

    No Known Activations