© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55161
    Prev
    Next
    INDEX
    Explanations

    connection and formation processes

    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
    Negative Logits
    äter
    -0.08
    ä¸įéĢļ
    -0.07
    OfType
    -0.07
    æŀģäºĨ
    -0.07
    asmine
    -0.06
    ijden
    -0.06
    zelf
    -0.06
    å¤ļåĩº
    -0.06
    _PARAMETERS
    -0.06
    ä¸įåĬ¨æijĩ
    -0.06
    POSITIVE LOGITS
     onto
    0.10
     into
    0.09
    มาà¸Īาà¸ģ
    0.09
    aturally
    0.08
    epend
    0.08
    æĢ§åľ°
    0.08
    /render
    0.08
    ikkan
    0.08
    istically
    0.08
    äºİ
    0.08
    Activations Density 0.269%

    No Known Activations