© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17401
    Prev
    Next
    INDEX
    Explanations

    mathematical variables with suffixes

    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
    جÙĨ
    -0.07
    endif
    -0.07
    áĢ»
    -0.07
    æĺĮ
    -0.07
    DAQ
    -0.07
    غÙĨ
    -0.06
    juana
    -0.06
    atis
    -0.06
    ISCO
    -0.06
    ocomplete
    -0.06
    POSITIVE LOGITS
    ä¸Ģçݯ
    0.07
    UME
    0.07
    ä¸Ģåı¶
    0.07
    zeit
    0.07
    ä¸Ģ对
    0.06
    wright
    0.06
    nou
    0.06
    Visible
    0.06
    _marks
    0.06
    åı¯åIJĮæŶ
    0.06
    Activations Density 0.029%

    No Known Activations