© 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. 2303
    Prev
    Next
    INDEX
    Explanations

    say "int"

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

    No Comments

    Negative Logits
     rút
    -17.13
    .appspot
    -16.88
    /demo
    -16.75
     Melissa
    -16.75
    百花
    -15.19
     kitty
    -14.94
    .trailing
    -14.44
    кро
    -14.31
    共振
    -14.31
    Mel
    -14.31
    POSITIVE LOGITS
     Int
    82.50
    int
    76.00
    Int
    75.50
     int
    72.50
    -int
    65.00
    _int
    63.75
    .int
    63.00
    (int
    60.25
    	Int
    59.75
    	int
    59.00
    Activations Density 0.363%

    No Known Activations