© 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. 9175
    Prev
    Next
    INDEX
    Explanations

    code structure `Deserialize`, `.in`

    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
    nitz
    -0.08
     Dew
    -0.07
    CORD
    -0.07
     Cord
    -0.07
     Fleming
    -0.07
    minster
    -0.07
    ä¿Ĺ
    -0.07
     OL
    -0.07
    ÑģÑĤка
    -0.06
    olk
    -0.06
    POSITIVE LOGITS
    ovich
    0.08
    NumberOf
    0.07
    åºĶåħĪ
    0.07
    åħĪæĺ¯
    0.07
    ehe
    0.07
    线æĿ¡
    0.07
    åĨħ容æıIJä¾Ľæĸ¹
    0.07
     Total
    0.06
    avigator
    0.06
    åºĶ该ä¸įä¼ļ
    0.06
    Activations Density 0.013%

    No Known Activations