© 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. 29740
    Prev
    Next
    INDEX
    Explanations

    date calculations, numbers, locations

    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
    åIJĽçļĦ
    -0.08
    èµĦæºIJç½ij
    -0.08
    åħ¨æľ¬å°ı说
    -0.08
    ัà¸Ļ
    -0.08
    κÏģι
    -0.08
     kalk
    -0.08
    -Jun
    -0.07
     McCart
    -0.07
    -Jan
    -0.07
    dll
    -0.07
    POSITIVE LOGITS
    游åĩ»
    0.07
    æµĻ
    0.06
    otec
    0.06
    úz
    0.06
    èĬ®
    0.06
     retract
    0.06
    æıIJåĢ¡
    0.06
    äck
    0.06
    çİ°
    0.06
    agraph
    0.06
    Activations Density 0.036%

    No Known Activations