© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11987
    Prev
    Next
    INDEX
    Explanations

    for purposes

    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
    াম
    -0.07
     пÑĢебÑĭваниÑı
    -0.06
    ç»ıåİĨ
    -0.06
    à¹ĥà¸Ĭà¹īà¸ļริà¸ģาร
    -0.06
    ãģĦãģª
    -0.06
    γÏĮ
    -0.06
    _COMPAT
    -0.06
     utilizando
    -0.06
     оÑĤÑģÑĥÑĤ
    -0.06
    éļıçĿĢ
    -0.05
    POSITIVE LOGITS
     purposes
    0.11
     Zwecke
    0.09
     ÑĨелей
    0.09
    ä¹ĭ缮çļĦ
    0.09
    weis
    0.08
    wards
    0.08
    åķĨä¸ļçĶ¨éĢĶ
    0.08
    åħ¨æł¡
    0.08
    stein
    0.07
     sake
    0.07
    Activations Density 0.329%

    No Known Activations