© 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. 31574
    Prev
    Next
    INDEX
    Explanations

    numbers and structure

    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
    ä¸įç®Ģåįķ
    -0.07
    trup
    -0.07
    åı°åİ¿
    -0.07
    积æŀģéħįåIJĪ
    -0.07
    ä¸į便
    -0.07
    æĺ¯å®¢æĪ·
    -0.06
    æĸ°åŁİ
    -0.06
    åIJĬ
    -0.06
    è¡ĮåĬ¨ä¸Ĭ
    -0.06
     Canter
    -0.06
    POSITIVE LOGITS
    ä»İä¸Ń
    0.08
    åıģ
    0.07
     among
    0.07
    ajos
    0.07
    INY
    0.07
    สà¸Ļ
    0.07
    among
    0.06
    /reference
    0.06
     likes
    0.06
     Congress
    0.06
    Activations Density 0.036%

    No Known Activations