© 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. 24799
    Prev
    Next
    INDEX
    Explanations

    integral of dx

    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
    arena
    -0.07
    两èĢħ
    -0.07
    åĨħå¤ĸ
    -0.07
     Bota
    -0.07
    大礼åĮħ
    -0.06
    ¬ģ
    -0.06
    weiler
    -0.06
    ENTA
    -0.06
    è¡Į驶æŶ
    -0.06
    CDATA
    -0.06
    POSITIVE LOGITS
    zik
    0.07
    stick
    0.07
    ombe
    0.07
    _PAR
    0.07
    atiques
    0.06
    å¹³è¡Į
    0.06
    রà§ĩ
    0.06
    جÙĪÙħ
    0.06
    å°±æĺ¯å¯¹
    0.06
    æ±Łå¤ı
    0.06
    Activations Density 0.006%

    No Known Activations