© 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. 1111
    Prev
    Next
    INDEX
    Explanations

    fly with

    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
    engt
    -0.08
    _attention
    -0.07
    ently
    -0.07
    Attention
    -0.07
    egen
    -0.07
    chenk
    -0.07
    urally
    -0.07
    详ç»ĨäºĨ解
    -0.07
    ly
    -0.07
    otime
    -0.07
    POSITIVE LOGITS
    尼迪
    0.07
    èĬ³èįī
    0.07
    ç«ĭäºİ
    0.07
    arshal
    0.06
    ложений
    0.06
    æłĩ
    0.06
    оÑĢа
    0.06
    æĿıèĬ±
    0.06
    ancia
    0.06
    帼
    0.06
    Activations Density 0.017%

    No Known Activations