© 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. 14531
    Prev
    Next
    INDEX
    Explanations

    say "uppercase abbreviations"

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

    No Comments

    Negative Logits
    vig
    -18.25
     Crowley
    -17.75
     giveaway
    -17.75
     TZ
    -16.88
    SSF
    -16.63
    GMT
    -16.63
    TZ
    -16.63
    .truth
    -16.50
    zung
    -16.38
    xBF
    -16.00
    POSITIVE LOGITS
    机动
    15.13
    idelity
    15.00
     fier
    14.81
    胖子
    14.63
     Pist
    14.38
    idor
    14.38
    nist
    14.31
    iris
    13.94
    异
    13.81
    doch
    13.81
    Activations Density 0.021%

    No Known Activations