© 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. 28445
    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
    жан
    -0.07
    éĢ¸
    -0.07
    åĩłä¹İ没æľī
    -0.07
     Instant
    -0.07
    é¹ıé£ŀ
    -0.07
     Hers
    -0.07
    PU
    -0.07
    பà¯įபà¯ģ
    -0.07
     instant
    -0.07
    åĭĻ
    -0.07
    POSITIVE LOGITS
    0.07
     Exterior
    0.07
    åij¨å¹´çºªå¿µ
    0.07
    mdb
    0.07
    0.07
    ç«¥åŃIJ
    0.07
    sil
    0.06
     ${(
    0.06
    æķĻå¸Īè¦ģ
    0.06
    çļĦ建议
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.