© 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. 1526
    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
     sound
    -58.50
    sound
    -53.75
     Sound
    -53.25
    Sound
    -52.50
     SOUND
    -50.50
     sounds
    -48.00
    _sound
    -44.50
     sounded
    -43.25
    声音
    -42.50
    _SOUND
    -42.00
    POSITIVE LOGITS
    Islam
    17.88
     Islam
    17.00
    _widgets
    16.38
    .widgets
    16.00
    ipy
    15.63
    DNA
    15.56
     Egypt
    15.44
    伊斯兰
    15.44
     DNA
    15.25
     CPF
    15.13
    Activations Density 0.113%

    No Known Activations