© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1070
    Prev
    Next
    INDEX
    Explanations

    do not say TV

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

    No Comments

    Negative Logits
    电视
    -54.00
     TV
    -52.00
     television
    -49.75
    TV
    -48.00
    電視
    -44.75
    电视机
    -44.25
     tv
    -43.50
     Television
    -43.25
    _TV
    -43.00
    -TV
    -42.50
    POSITIVE LOGITS
    马
    16.50
    蚕
    14.00
     Sym
    13.94
     Code
    13.81
    Sym
    13.69
    -coded
    13.56
    内马
    13.50
    ogne
    13.44
     Codes
    13.31
    柜台
    13.00
    Activations Density 0.085%

    No Known Activations