© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14463
    Prev
    Next
    INDEX
    Explanations

    say publication

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

    No Comments

    Negative Logits
    ier
    -16.88
    archical
    -15.50
    ieren
    -14.19
     Viet
    -13.81
    -script
    -13.38
    (store
    -13.31
    (meta
    -13.31
    iers
    -13.19
    (handle
    -13.13
    (h
    -13.06
    POSITIVE LOGITS
    utral
    17.25
     publication
    16.25
    LAY
    16.13
    陛
    16.00
    publication
    15.63
    媒体
    15.63
    新闻发布
    15.38
    INO
    15.19
    屁
    15.19
    版权归
    15.13
    Activations Density 0.128%

    No Known Activations