© 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. 41814
    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
    à¸Ńà¸Ļà¸Ķà¹Į
    -0.10
    -monitor
    -0.09
    ActionCode
    -0.09
    оÑĢÑĤи
    -0.09
    enny
    -0.08
    trup
    -0.08
    egt
    -0.08
    acker
    -0.08
     rifl
    -0.08
    नाव
    -0.08
    POSITIVE LOGITS
    0.07
     c
    0.07
    mar
    0.06
    æĪIJ绩
    0.06
     during
    0.06
     in
    0.06
     C
    0.06
     s
    0.06
    åŃ¦ä¹łæĪIJ绩
    0.06
    te
    0.06
    Activations Density 0.000%

    No Known Activations