© 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. 1585
    Prev
    Next
    INDEX
    Explanations

    harmony

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

    No Comments

    Negative Logits
     hash
    -29.38
    Har
    -29.13
     Hash
    -28.75
     Harmon
    -28.75
    har
    -28.63
     Har
    -27.88
     harmon
    -27.63
     harmonic
    -27.25
    Hash
    -26.63
     гар
    -26.38
    POSITIVE LOGITS
    CPU
    16.00
    Python
    15.81
    读后
    15.69
    GPU
    15.31
    _python
    15.13
     CPU
    15.00
    ESPN
    14.94
     Python
    14.56
    ран
    14.31
    PYTHON
    14.31
    Activations Density 0.099%

    No Known Activations