© 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. 1938
    Prev
    Next
    INDEX
    Explanations

    say audio

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

    No Comments

    Negative Logits
     math
    -19.38
    甲
    -18.25
     Math
    -17.75
    meth
    -17.50
     Meth
    -17.38
    _math
    -17.13
    ether
    -17.00
     meth
    -16.63
    法
    -16.50
     Macedonia
    -16.50
    POSITIVE LOGITS
    _AUDIO
    24.88
    AUDIO
    24.25
    audio
    23.88
    音频
    23.38
     audio
    23.38
    .Audio
    22.88
    _audio
    22.75
    Audio
    22.13
     Audio
    22.00
    音乐
    21.88
    Activations Density 0.327%

    No Known Activations