© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 16257
    Prev
    Next
    INDEX
    Explanations

    [parad] => [ms]

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

    No Comments

    Negative Logits
     Hubb
    -16.25
    ISP
    -15.56
    net
    -14.88
    nel
    -14.69
    orsk
    -14.06
    обра
    -14.00
    apg
    -14.00
    nels
    -13.94
     Spr
    -13.81
    .Getter
    -13.69
    POSITIVE LOGITS
    辞职
    17.38
     centrif
    16.50
    悬挂
    16.50
     sediment
    16.50
     CIF
    16.13
     TICK
    15.88
    bic
    15.75
     semiclassical
    15.69
    灯
    15.63
     sed
    15.56
    Activations Density 0.128%

    No Known Activations