© 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. 4471
    Prev
    Next
    INDEX
    Explanations

    aerial, internal, surface

    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
    ulet
    -0.08
    é£ŀé¾Ļ
    -0.07
    ÙĮ
    -0.06
    Ö¸
    -0.06
    ترÙĨت
    -0.06
    iquement
    -0.06
    .fromCharCode
    -0.06
     جÙĦÙĪ
    -0.06
    åľ¨æľĢåIJİ
    -0.06
    asih
    -0.06
    POSITIVE LOGITS
    à¸ķัวà¸Ĥà¸Ńà¸ĩ
    0.14
    à¹Ģà¸Ļืà¹īà¸Ńหาà¸Ĥà¸Ńà¸ĩ
    0.14
    สำà¸Ħัà¸įà¸Ĥà¸Ńà¸ĩ
    0.14
    à¸ģารà¸Ĺำà¸ĩาà¸Ļà¸Ĥà¸Ńà¸ĩ
    0.11
    หà¸Ļึà¹Īà¸ĩà¸Ĥà¸Ńà¸ĩ
    0.11
    à¹ģรà¸ģà¸Ĥà¸Ńà¸ĩ
    0.11
    สà¹Īวà¸Ļà¸Ĥà¸Ńà¸ĩ
    0.09
    à¹ĥหมà¹Īà¸Ĥà¸Ńà¸ĩ
    0.09
     của
    0.09
    ระà¸ļาà¸Ķà¸Ĥà¸Ńà¸ĩ
    0.08
    Activations Density 0.889%

    No Known Activations