© 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. 14498
    Prev
    Next
    INDEX
    Explanations

    say "rare fragments"

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

    No Comments

    Negative Logits
    weed
    -19.13
    drs
    -18.38
    immers
    -18.00
    _Cl
    -17.75
    GridColumn
    -17.63
    粉
    -17.50
     Cherry
    -17.25
    粉末
    -17.13
    槌
    -17.00
     Radiation
    -16.88
    POSITIVE LOGITS
    stk
    16.75
     stab
    15.69
    qp
    15.19
    stab
    15.13
     sik
    14.94
    鲂
    14.75
     stad
    14.44
    trl
    14.25
    berg
    14.25
    ulk
    14.13
    Activations Density 0.745%

    No Known Activations