© 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. 48205
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
     GPI
    -0.06
    âĢ¦
    -0.06
    Ùģا
    -0.06
    chon
    -0.06
    è¿ĺæľīä»Ģä¹Ī
    -0.06
    çĮľä½łåĸľæ¬¢
    -0.06
     Messina
    -0.06
     mÃŃt
    -0.06
    ÄįenÃŃ
    -0.06
     $($
    -0.06
    POSITIVE LOGITS
    icher
    0.09
    æŨ
    0.07
    isFunction
    0.07
    ä»Ĭ天å°ıç¼ĸå°±
    0.07
    CONN
    0.07
    egy
    0.07
    :type
    0.07
    顺å¿ĥ
    0.07
    iced
    0.07
    en
    0.07
    Activations Density 0.044%

    No Known Activations