© 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. 11820
    Prev
    Next
    INDEX
    Explanations

    XML namespace schema location

    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
    ØŃÙĬÙĨ
    -0.07
    ascal
    -0.07
    undes
    -0.07
    erc
    -0.07
     ruá»Ļt
    -0.07
    ettet
    -0.07
    alley
    -0.07
    ilon
    -0.07
    semble
    -0.07
    CTION
    -0.07
    POSITIVE LOGITS
    isto
    0.07
    ystick
    0.06
    缴æİ¥æĪĸ
    0.06
    æĪIJæīį
    0.06
     endors
    0.06
    SingleNode
    0.06
     sust
    0.06
    åĬĽå¼º
    0.06
    posa
    0.06
    ä¹ĭä¸ī
    0.06
    Activations Density 0.005%

    No Known Activations