© 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. 15210
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

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

    No Comments

    Negative Logits
    棋牌
    -26.38
    OWL
    -25.75
     Motorcycle
    -25.50
     Estonia
    -25.25
    aub
    -24.88
    Drupal
    -24.88
    Chess
    -24.75
     cud
    -24.63
    websocket
    -24.50
    bitcoin
    -24.38
    POSITIVE LOGITS
    /or
    12.63
    /her
    10.69
    gether
    10.31
    2
    9.56
    ‐
    9.38
    此基础上
    9.38
    ️
    9.31
     fucking
    9.19
    0
    9.06
    1
    9.00
    Activations Density 24.489%

    No Known Activations