© 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. 2250
    Prev
    Next
    INDEX
    Explanations

    say system attributes

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

    No Comments

    Negative Logits
    百
    -23.63
    万
    -21.00
    千
    -18.13
     fig
    -18.13
    萬
    -17.13
     cent
    -17.00
     max
    -16.88
     mil
    -16.38
     thousand
    -15.75
     Cent
    -14.88
    POSITIVE LOGITS
    modal
    26.13
    structural
    25.38
    minimal
    25.38
     structural
    25.13
     operational
    25.00
     modal
    25.00
    Minimal
    23.88
     minimal
    23.75
     administrative
    23.63
     Operational
    23.63
    Activations Density 0.329%

    No Known Activations