© 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. 14589
    Prev
    Next
    INDEX
    Explanations

    prehistoric ages

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

    No Comments

    Negative Logits
    edBy
    -16.63
    Gay
    -15.31
    (cs
    -14.81
    免除
    -14.81
    .um
    -14.75
    erno
    -14.56
    (points
    -14.56
    parsers
    -14.50
    ardi
    -14.38
    \uD
    -14.38
    POSITIVE LOGITS
    ños
    13.13
    чет
    12.94
    mino
    12.94
    jourd
    12.75
     Pret
    12.75
    近三年
    12.50
    ço
    12.44
    �
    12.38
    .prepend
    12.31
    irmware
    12.13
    Activations Density 0.071%

    No Known Activations