© 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. 15301
    Prev
    Next
    INDEX
    Explanations

    say newline

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

    No Comments

    Negative Logits
    镲
    -17.63
    iland
    -17.00
     Pierce
    -16.75
    elts
    -15.75
    hammer
    -15.69
    luet
    -15.69
    拍拍
    -14.88
     Lam
    -14.44
     Liam
    -14.38
    enties
    -14.19
    POSITIVE LOGITS
    gor
    16.63
    igor
    16.38
    utra
    15.88
    geh
    15.44
    blr
    15.00
    fra
    14.88
    _bi
    14.81
     dru
    14.75
    gro
    14.63
    /fr
    14.56
    Activations Density 0.058%

    No Known Activations