© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14949
    Prev
    Next
    INDEX
    Explanations

    virus

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

    No Comments

    Negative Logits
    浣
    -19.75
    .cv
    -19.25
    anst
    -19.13
    evt
    -18.75
    ave
    -18.50
     Sew
    -18.38
    _lv
    -18.25
     sant
    -18.13
    ainted
    -18.00
    สว
    -18.00
    POSITIVE LOGITS
    idal
    20.00
    amac
    18.50
    pac
    18.50
    itel
    18.50
    toc
    18.13
    tok
    18.13
     Zika
    17.25
     Gibson
    16.88
     Erick
    16.75
    pag
    16.63
    Activations Density 0.978%

    No Known Activations