© 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. 15302
    Prev
    Next
    INDEX
    Explanations

    initials

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

    No Comments

    Negative Logits
    姥
    -19.00
    葵
    -17.88
    TEM
    -17.75
    苔
    -17.75
     LUA
    -17.75
     CSI
    -17.50
    (kv
    -17.38
    用户名
    -17.38
    _PWM
    -17.25
    ERM
    -17.13
    POSITIVE LOGITS
     Pro
    18.13
    Pro
    17.75
     pro
    17.25
    pro
    16.38
    脯
    16.25
    .pro
    15.13
    izable
    15.13
    ilians
    14.88
    -Pro
    14.44
    6
    14.06
    Activations Density 0.133%

    No Known Activations