© 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. 1936
    Prev
    Next
    INDEX
    Explanations

    do not say sound

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

    No Comments

    Negative Logits
    声
    -37.25
    聲
    -32.75
    声响
    -29.63
    声音
    -28.13
    聲音
    -27.50
    的声音
    -27.13
     sound
    -26.38
     Sound
    -25.50
     acoustic
    -24.63
     voice
    -24.38
    POSITIVE LOGITS
    eki
    17.25
    .repaint
    16.38
     Java
    16.25
    伊斯兰
    15.88
    迪
    15.81
    新疆
    15.69
    �
    15.25
     Islamic
    15.19
    wood
    15.06
     Moroccan
    15.06
    Activations Density 0.044%

    No Known Activations