© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16298
    Prev
    Next
    INDEX
    Explanations

    say session

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

    No Comments

    Negative Logits
    总承包
    -16.00
    getDrawable
    -15.50
    压迫
    -15.31
     projector
    -14.88
    矿泉水
    -14.63
     Luz
    -14.50
    .docker
    -14.50
    _PRESS
    -14.50
     outputStream
    -14.31
    ��
    -14.31
    POSITIVE LOGITS
     session
    47.00
     Session
    43.50
    Session
    43.25
     sessions
    42.50
    -session
    42.00
    session
    41.50
     SESSION
    41.00
    _session
    40.50
    Sessions
    39.75
     Cookie
    39.50
    Activations Density 0.071%

    No Known Activations