© 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. 49897
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    antara
    -0.08
    pers
    -0.07
    对ä¸ĢäºĽ
    -0.07
    åĬłä¸Ĭ
    -0.07
    åĬłä¹ĭ
    -0.07
    éĥ¨åĴĮ
    -0.07
     плÑİÑģ
    -0.07
    缸éļı
    -0.07
    è¿Ļä¸İ
    -0.07
    .setDefault
    -0.07
    POSITIVE LOGITS
    alay
    0.07
    кÑĥÑĢ
    0.07
    elsen
    0.07
    asseur
    0.07
     employ
    0.07
    edd
    0.06
    untime
    0.06
    计ç®Ĺåĩº
    0.06
    tev
    0.06
     racc
    0.06
    Activations Density 0.068%

    No Known Activations