© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2970
    Prev
    Next
    INDEX
    Explanations

    say prop

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

    No Comments

    Negative Logits
     ER
    -17.50
     mercury
    -15.00
    lish
    -14.88
    ymi
    -14.50
    _lat
    -14.25
    UTE
    -14.19
     LAT
    -14.19
     Lat
    -14.13
     Donate
    -14.00
    emie
    -13.94
    POSITIVE LOGITS
     prop
    94.00
     Prop
    93.00
    prop
    90.50
    Prop
    86.50
    (prop
    81.00
    	prop
    80.50
    -prop
    79.00
    _prop
    78.00
    .Prop
    76.00
    .prop
    75.50
    Activations Density 0.358%

    No Known Activations