© 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. 50992
    Prev
    Next
    INDEX
    Explanations

    either or

    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
    ayi
    -0.07
    irik
    -0.07
    å±ı
    -0.06
    reste
    -0.06
    åĦ¿å¥³
    -0.06
    _online
    -0.06
    好å¿ĥ
    -0.06
     Sod
    -0.06
    æĺ¯ä¼ļ
    -0.06
    arm
    -0.06
    POSITIVE LOGITS
     independents
    0.08
     imperf
    0.08
    è¸ıè¸ıå®ŀ
    0.08
     compensate
    0.07
    ë¡ł
    0.07
    ivy
    0.07
    åŃ¦å¦¹
    0.07
    llib
    0.07
    à¸Ńา
    0.07
    åĢĴåľ¨
    0.07
    Activations Density 0.110%

    No Known Activations