© 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. 55967
    Prev
    Next
    INDEX
    Explanations

    control layer column Element nodes endpoints step

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     remis
    -0.07
    è¿Ļå¥Ĺ
    -0.07
    ÏĥÏĦÏĮ
    -0.07
    undy
    -0.07
    eer
    -0.06
    èĶļ
    -0.06
    æľĹæľĹ
    -0.06
    valueOf
    -0.06
    )index
    -0.06
    è®°å¿ĨçļĦ
    -0.06
    POSITIVE LOGITS
    ç±»åŀĭ为
    0.09
    à¸Ľà¸£à¸°à¹Ģà¸łà¸Ĺ
    0.09
    OfType
    0.09
    ç±»åŀĭ
    0.08
     placed
    0.08
     types
    0.08
    åĪĽå»º
    0.08
    YPE
    0.08
    ç±»åŀĭçļĦ
    0.08
    é¡ŀåŀĭ
    0.08
    Activations Density 0.218%

    No Known Activations