© 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. 31936
    Prev
    Next
    INDEX
    Explanations

    website code and product names

    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
     halnya
    -0.09
    aÄĩ
    -0.09
    以ä¸Ĭå°±æĺ¯å°ıç¼ĸ
    -0.09
    amanan
    -0.09
    edReader
    -0.08
    sWith
    -0.08
    aos
    -0.08
    zinho
    -0.08
    <<<<<<<
    -0.08
    以ä¸Ĭå°±æĺ¯åħ³äºİ
    -0.08
    POSITIVE LOGITS
    ousel
    0.08
    atre
    0.08
    ric
    0.07
    ת
    0.07
    رة
    0.07
    à³ģ
    0.07
    ERIC
    0.07
     selben
    0.07
    erguson
    0.06
    á»ĥn
    0.06
    Activations Density 9.029%

    No Known Activations