© 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. 23609
    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
    好å¤ļ
    -0.08
    oleh
    -0.07
    ly
    -0.07
    åIJīæĢĿ
    -0.07
    éĺĻ
    -0.06
    ¯
    -0.06
    olak
    -0.06
    keeper
    -0.06
    unsch
    -0.06
     Haar
    -0.06
    POSITIVE LOGITS
    èĢģå¸Īåľ¨
    0.07
    ´
    0.07
    gäng
    0.07
    家ä¹IJ
    0.07
     informing
    0.07
    ç²±
    0.07
    _ABC
    0.07
    adel
    0.07
    arer
    0.06
    åĩ¯è¿ª
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.