© 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. 2022
    Prev
    Next
    INDEX
    Explanations

    do not say ball

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

    No Comments

    Negative Logits
    球
    -59.25
     ball
    -56.25
    ball
    -50.75
    Ball
    -50.50
    BALL
    -49.75
     Ball
    -49.75
     balls
    -49.25
    -ball
    -49.00
     BALL
    -48.75
    _ball
    -48.25
    POSITIVE LOGITS
    Michigan
    15.94
    印尼
    15.19
    文本
    15.06
    湘西
    14.50
     Michigan
    14.19
    芬兰
    14.00
    Mexico
    13.81
    戎
    13.63
     textures
    13.56
     texto
    13.44
    Activations Density 0.083%

    No Known Activations