© 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. 64780
    Prev
    Next
    INDEX
    Explanations

    actions like add, remove, do

    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
    fty
    -0.08
    naire
    -0.07
    åºĶéģ¿åħį
    -0.07
    inston
    -0.07
    æľī好çļĦ
    -0.07
    åĽ¢æĪIJåijĺ
    -0.07
    羣æŃ£æĪIJ为
    -0.07
    à¸Ļะà¸Ħะ
    -0.07
    PropertyDescriptor
    -0.07
    masin
    -0.07
    POSITIVE LOGITS
     admittedly
    0.08
    rata
    0.07
    èĤīçľ¼
    0.07
    æİ¥ä¸ĭæĿ¥
    0.07
     quite
    0.07
    ç¨įå¾®
    0.07
     ðŁĻĤ
    0.07
     ðŁij
    0.07
    顾åIJįæĢĿä¹ī
    0.07
     basically
    0.07
    Activations Density 2.462%

    No Known Activations