© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 756
    Prev
    Next
    INDEX
    Explanations

    say te

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

    No Comments

    Negative Logits
     Alberta
    -24.63
    甘肃省
    -24.50
     Scotland
    -24.00
     Icelandic
    -23.75
    甘肃
    -23.50
     Vermont
    -23.25
    加拿大
    -23.25
    新西兰
    -23.13
    无锡
    -22.63
     Iceland
    -22.50
    POSITIVE LOGITS
     Te
    27.50
     te
    23.63
    Te
    21.25
    (te
    20.00
    .te
    18.88
    _ta
    18.00
     Ta
    17.88
    .Te
    17.63
    Tur
    17.63
    Ta
    17.38
    Activations Density 0.043%

    No Known Activations