© 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. 33707
    Prev
    Next
    INDEX
    Explanations

    summation, integration, association, invention

    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
    arton
    -0.07
    çŃīåIJĮ
    -0.06
    رب
    -0.06
    ãģŁãģł
    -0.06
    å¦Ĥä»ĬçļĦ
    -0.06
    佳人
    -0.06
    æ§ĺ
    -0.06
    æķĻèĤ²èĢĥè¯ķ
    -0.06
     dime
    -0.06
    çī
    -0.06
    POSITIVE LOGITS
    filer
    0.08
    æľīç¦ı
    0.07
    iring
    0.07
    бок
    0.07
    ",{
    0.07
    éģįäºĨ
    0.07
    个èµŀ
    0.07
    urement
    0.07
    -ever
    0.07
    ä¸Ģä¼ļ
    0.07
    Activations Density 0.002%

    No Known Activations