© 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. 15136
    Prev
    Next
    INDEX
    Explanations

    binary assignments

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

    No Comments

    Negative Logits
    胭
    -18.75
    尔斯
    -18.00
     Tango
    -16.75
    ystate
    -15.88
     cervical
    -15.81
    缢
    -15.81
     cerv
    -15.50
     Musk
    -15.50
    觞
    -15.31
    美术馆
    -15.06
    POSITIVE LOGITS
    zen
    16.88
    _tr
    16.25
    tr
    15.50
    EMPL
    15.25
    hom
    15.06
    (tr
    14.88
    利用
    14.50
    tri
    14.31
    Template
    14.19
    规划
    14.06
    Activations Density 0.034%

    No Known Activations