© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14586
    Prev
    Next
    INDEX
    Explanations

    say seven

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

    No Comments

    Negative Logits
    UTOR
    -16.63
     تس
    -13.94
    rowned
    -13.06
    准入
    -13.00
     portraits
    -13.00
    otate
    -13.00
    请点击
    -12.88
     lost
    -12.75
    erne
    -12.63
    低位
    -12.63
    POSITIVE LOGITS
     seven
    45.00
    7
    44.00
     Seven
    41.25
    七
    40.50
     seventh
    40.25
    七个
    40.25
    seven
    38.50
    ７
    36.00
    第七
    35.75
    Seven
    35.50
    Activations Density 1.078%

    No Known Activations