© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 592
    Prev
    Next
    INDEX
    Explanations

    N/A

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

    No Comments

    Negative Logits
     Tah
    -16.13
     Netz
    -15.94
     �
    -15.88
    kah
    -15.19
    Jak
    -15.06
    જ
    -15.06
    thane
    -15.00
    Tok
    -15.00
    cy
    -14.94
    spy
    -14.88
    POSITIVE LOGITS
     Hispan
    19.50
    雀
    17.00
    ideon
    16.50
    .lineTo
    16.25
    ivery
    16.25
    锇
    16.13
    ledo
    15.69
    DBC
    15.50
     canvas
    15.50
     Alonso
    15.25
    Activations Density 0.049%

    No Known Activations