© 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. 731
    Prev
    Next
    INDEX
    Explanations

    say "mongo"

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

    No Comments

    Negative Logits
    汶
    -21.25
     Pasadena
    -19.13
     Holland
    -18.88
    潍坊
    -18.88
     Kawasaki
    -18.50
    峡
    -18.13
    (wp
    -18.00
    Ĵ
    -17.88
     PAL
    -17.88
    德州
    -17.75
    POSITIVE LOGITS
    Mongo
    57.00
     mongo
    56.00
     Mongo
    55.25
    mongo
    54.25
     MongoDB
    53.75
    .mongo
    52.50
     mongodb
    52.00
    .Mongo
    49.75
    .mongodb
    49.25
    mongodb
    49.00
    Activations Density 0.090%

    No Known Activations