© 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. 34157
    Prev
    Next
    INDEX
    Explanations

    C# code and programming

    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
    è·Łä¸įä¸Ĭ
    -0.09
    neau
    -0.08
    æŃ¥åŃIJ
    -0.08
    igas
    -0.08
    åħ¸èĹı
    -0.08
    pron
    -0.08
    rück
    -0.08
    æĬµæĮ¡
    -0.08
    iglio
    -0.08
    éĢ¼è¿ij
    -0.08
    POSITIVE LOGITS
    à¸Ńยูà¹Īà¹ģลà¹īว
    0.08
    å·²çŁ¥
    0.08
    åı¦ä¸Ģ
    0.08
    åı¦ä¸Ģ个
    0.07
    çĿ«æ¯Ľ
    0.07
    ä¹ŀ
    0.06
    åijĬ
    0.06
    å½¼
    0.06
     obvious
    0.06
     cluster
    0.06
    Activations Density 0.005%

    No Known Activations