© 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. 39197
    Prev
    Next
    INDEX
    Explanations

    no or required

    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
    arshal
    -0.07
    ä¸į解
    -0.07
    å°Ķå¾·
    -0.06
     along
    -0.06
     deb
    -0.06
    bian
    -0.06
    ä¸Ŀ
    -0.06
    ä¸įå¤į
    -0.06
    ä¸įéĹ´æĸŃ
    -0.06
    æľ¬æĸĩéĵ¾æİ¥
    -0.06
    POSITIVE LOGITS
    avel
    0.08
    _INITIALIZER
    0.08
     ormai
    0.08
    omy
    0.07
    igin
    0.07
    rapper
    0.07
    öp
    0.07
    à¹īà¸Ńà¸ĩ
    0.07
    lopen
    0.07
    å¿ĥæĢ¥
    0.07
    Activations Density 0.011%

    No Known Activations