© 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. 13424
    Prev
    Next
    INDEX
    Explanations

    network structure

    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
    å°ĶèĴĻ
    -0.08
    окÑģи
    -0.08
    à¹Īาà¸Ļ
    -0.08
     Justi
    -0.08
    ZION
    -0.08
    aisse
    -0.08
    jni
    -0.07
    oksi
    -0.07
    ISMATCH
    -0.07
    ä¸ĵ家表示
    -0.07
    POSITIVE LOGITS
    æľ¬èº«
    0.07
    åĬ©
    0.07
    kak
    0.07
    بÙĪد
    0.06
    son
    0.06
    并ç»ĵåIJĪ
    0.06
    akar
    0.06
    æľ¬èº«çļĦ
    0.06
    å±ŀæĢ§åĴĮ
    0.06
    é£Ł
    0.06
    Activations Density 0.034%

    No Known Activations