© 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. 51332
    Prev
    Next
    INDEX
    Explanations

    etc

    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
    ierer
    -0.08
    西èĴĻ
    -0.08
    ervo
    -0.08
    -ever
    -0.08
    æĽ´å¤ļåĨħ容
    -0.08
    रà¥įफ
    -0.07
    itches
    -0.07
    bidden
    -0.07
    家éŨ
    -0.07
    endum
    -0.07
    POSITIVE LOGITS
    ลฯ
    0.07
    ä¸įä¸Ģ
    0.07
    aning
    0.06
    ety
    0.06
    avo
    0.06
    æĢ»ä¹ĭ
    0.06
    ogan
    0.06
    ..\
    0.06
     dozen
    0.06
    ka
    0.06
    Activations Density 0.068%

    No Known Activations