© 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. 11272
    Prev
    Next
    INDEX
    Explanations

    list of items/names

    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
    ão
    -0.07
    ÙĬÙĦØ©
    -0.07
    oomla
    -0.07
    teman
    -0.07
    ILES
    -0.07
    çĽ¸ä¼¼æĸĩçĮ®
    -0.07
    eres
    -0.07
    ience
    -0.07
    quement
    -0.07
    mung
    -0.07
    POSITIVE LOGITS
     encodeURIComponent
    0.07
     etc
    0.06
    æİĴè¡Į
    0.06
    çŃīçŃī
    0.06
    ä¹ĭ乡
    0.06
    नि
    0.06
     gre
    0.06
     ë¹Ħ롯íķľ
    0.06
    åħ¬åı¸çŃī
    0.06
    eliers
    0.06
    Activations Density 0.091%

    No Known Activations