© 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. 1728
    Prev
    Next
    INDEX
    Explanations

    times or counts

    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
    æĿ¥èĩªç½ij绾
    -0.07
    keleton
    -0.07
    åĪ»éª¨
    -0.07
     Mapper
    -0.07
     [,
    -0.07
    ×Ĺ׳×ķ
    -0.07
    innen
    -0.06
    .ini
    -0.06
     вÑģ
    -0.06
    мам
    -0.06
    POSITIVE LOGITS
    åĢįçļĦ
    0.12
     times
    0.09
    åĢį
    0.09
    _TIMES
    0.08
     multiples
    0.08
    纬
    0.08
     Times
    0.07
     TIMES
    0.07
    ç«ĭåį³çĶ³è¯·
    0.07
    åĢį以ä¸Ĭ
    0.07
    Activations Density 0.062%

    No Known Activations