© 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. 11163
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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
    ÙĬت
    -0.07
    AKE
    -0.06
    ä¸İå°ı
    -0.06
    °
    -0.06
    zte
    -0.06
     reference
    -0.06
    _GL
    -0.06
    USAGE
    -0.06
    人ä¸İ
    -0.06
     Ñģк
    -0.06
    POSITIVE LOGITS
    èĪĴéĢĤ度
    0.08
     Fanpage
    0.07
     Liebl
    0.07
     Perugia
    0.07
    ாத
    0.07
    Õ·
    0.07
    igenza
    0.07
    ä¸ĢçĤ¹ä¸Ģæ»´
    0.06
    åİĨ
    0.06
    .Designer
    0.06
    Activations Density 0.015%

    No Known Activations