© 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. 15166
    Prev
    Next
    INDEX
    Explanations

    say "光" words

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

    No Comments

    Negative Logits
    öh
    -19.13
    $log
    -18.25
    インド
    -17.88
     Poke
    -17.50
    ać
    -17.50
    .LOG
    -17.38
    ardware
    -17.13
    锆
    -16.75
    luet
    -16.50
     Suicide
    -16.50
    POSITIVE LOGITS
    值得关注
    13.75
     wonder
    13.44
    cl
    12.75
    Trans
    12.69
    戎
    12.69
    Pre
    12.38
    Q
    12.38
    改
    12.19
    以为
    12.19
    Star
    12.13
    Activations Density 0.086%

    No Known Activations