© 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. 8754
    Prev
    Next
    INDEX
    Explanations

    multiple, double, iv, ivalent

    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
    xico
    -0.09
    ÙĪرÙĥ
    -0.08
    æīŃ
    -0.08
    unday
    -0.07
    orza
    -0.07
    ifo
    -0.07
    çĻ½é©¬
    -0.07
    ovas
    -0.07
    iles
    -0.07
    ä¸Ģ段
    -0.07
    POSITIVE LOGITS
     consecutive
    0.09
     successive
    0.09
     sequential
    0.08
    æĢ»ä»·
    0.08
    累计
    0.08
    новÑĢемен
    0.07
    Sequential
    0.07
    çŁŃæŶéĹ´åĨħ
    0.07
     consec
    0.07
     cumulative
    0.07
    Activations Density 0.033%

    No Known Activations