© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 65122
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    缮çŀª
    -0.09
    azz
    -0.08
    azzi
    -0.07
    粤港澳
    -0.07
    è¿Ļ个社ä¼ļ
    -0.07
    ones
    -0.07
    _DESCRIPTOR
    -0.07
    ä¸įä¸ĭæĿ¥
    -0.07
    rum
    -0.07
    æŀģå°ij
    -0.07
    POSITIVE LOGITS
    åį¿
    0.08
     gelungen
    0.07
    æ¯ıå°ıé¢ĺ
    0.07
    窦
    0.07
    kl
    0.06
    oe
    0.06
     Stout
    0.06
     dope
    0.06
    atego
    0.06
     relent
    0.06
    Activations Density 0.000%

    No Known Activations