© 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. 15095
    Prev
    Next
    INDEX
    Explanations

    say 9

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

    No Comments

    Negative Logits
    iston
    -16.88
    antu
    -16.50
    urnal
    -15.63
     bada
    -15.06
    cla
    -14.88
    ansson
    -14.63
    bö
    -14.44
    ila
    -14.38
    devil
    -14.38
    实事求是
    -14.31
    POSITIVE LOGITS
     Kerr
    15.25
     lot
    14.25
     đám
    13.25
    setMax
    13.13
    xfff
    12.81
    黎
    12.75
    ечен
    12.56
    ignite
    12.56
    退役
    12.50
    lep
    12.44
    Activations Density 0.042%

    No Known Activations