© 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. 14929
    Prev
    Next
    INDEX
    Explanations

    article an

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

    No Comments

    Negative Logits
     Ferd
    -17.50
    rema
    -16.63
    itat
    -16.38
    itate
    -15.88
    拐
    -15.25
    STANCE
    -15.13
    plotlib
    -15.13
    .Dispatch
    -14.81
    TRACT
    -14.56
    &M
    -14.50
    POSITIVE LOGITS
     place
    15.50
    term
    14.94
    ellar
    14.25
    тер
    13.88
    ory
    13.81
    orm
    13.50
    irty
    13.44
    arden
    13.19
     tongue
    12.94
     germ
    12.88
    Activations Density 0.195%

    No Known Activations