© 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. 39025
    Prev
    Next
    INDEX
    Explanations

    of [process/purpose]

    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
    اÙĨÙĩ
    -0.08
    -BEGIN
    -0.08
    anyl
    -0.07
    vably
    -0.07
    ç´§äºĨ
    -0.07
     nhÃłng
    -0.07
    ILLED
    -0.07
     Folg
    -0.07
    ptides
    -0.07
    个èµŀ
    -0.07
    POSITIVE LOGITS
    æķĻèĤ²æĺ¯
    0.08
    å·¥ä½ľçļĦåIJĮæŶ
    0.07
    /workspace
    0.07
    éħİ
    0.07
    çļĦè¿ĺæľī
    0.06
    á»±
    0.06
     approach
    0.06
     interest
    0.06
    Ø·Ùģ
    0.06
    ÙħÙĬ
    0.06
    Activations Density 0.599%

    No Known Activations