© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15106
    Prev
    Next
    INDEX
    Explanations

    number with operator

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

    No Comments

    Negative Logits
    _ray
    -17.75
     Tart
    -17.63
     Hann
    -17.63
    DDS
    -17.50
     TTC
    -16.88
    ಡ
    -16.88
    _od
    -16.75
     SST
    -16.63
    ­tion
    -16.63
    §
    -16.63
    POSITIVE LOGITS
    武林
    18.75
    音乐会
    17.75
     motorcycle
    17.25
    温室
    16.75
    anime
    16.63
     motorcycles
    16.13
     Ashe
    15.69
    鞍
    15.44
    寺庙
    15.38
    农家乐
    15.38
    Activations Density 0.024%

    No Known Activations