© 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. 29952
    Prev
    Next
    INDEX
    Explanations

    counts of people or items

    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
    orre
    -0.08
    erras
    -0.07
    .story
    -0.07
     Mej
    -0.06
    herr
    -0.06
    »
    -0.06
    -regexp
    -0.06
    以对
    -0.06
    以åĪ©
    -0.06
    æ·¡æ·¡
    -0.06
    POSITIVE LOGITS
    ogan
    0.07
    é¢Ŀå¤ĸçļĦ
    0.07
    _additional
    0.07
    uvan
    0.07
    ucas
    0.07
     thêm
    0.07
    åĬ
    0.06
     additional
    0.06
    ä»ģ
    0.06
    娩
    0.06
    Activations Density 0.002%

    No Known Activations