© 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. 25306
    Prev
    Next
    INDEX
    Explanations

    CVirtThread, StringSearchable, IndianBlend.com, YourAmateurPorn, Deep Creek, batStat, EditorCell, index.php, AxWindowsMediaPlayer, CONF_MESSAGE

    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
    çļĩ
    -0.07
    认
    -0.07
    Calls
    -0.07
    å¿
    -0.06
    à¹īา
    -0.06
    å«£
    -0.06
    ева
    -0.06
    .Encode
    -0.06
    身临åħ¶å¢ĥ
    -0.06
    汪æ´ĭ
    -0.06
    POSITIVE LOGITS
    ocos
    0.07
    oli
    0.06
    neze
    0.06
    etsy
    0.06
    ¼
    0.06
    ÙħÙĪÙĦ
    0.06
    iet
    0.06
     late
    0.06
    peak
    0.06
    å®ĮæĪIJ
    0.06
    Activations Density 1.661%

    No Known Activations