© 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. 1057
    Prev
    Next
    INDEX
    Explanations

    气血

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

    No Comments

    Negative Logits
    游泳
    -21.63
    山水
    -18.63
     Maher
    -17.75
     ICT
    -17.75
    StreamWriter
    -17.13
     γ
    -17.13
    梅西
    -17.13
     stream
    -16.88
    山西
    -16.75
    Stream
    -16.63
    POSITIVE LOGITS
     Laud
    16.50
    .paper
    15.94
    篷
    15.44
    Na
    15.06
    _menu
    14.88
     european
    14.81
    (stat
    14.56
    ARGET
    14.50
    lang
    14.44
    inas
    14.44
    Activations Density 0.306%

    No Known Activations