© 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. 11530
    Prev
    Next
    INDEX
    Explanations

    figures and numbers

    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
    é¾Ļä¹ĭ
    -0.07
    æī«çłģåħ³æ³¨
    -0.07
    otine
    -0.07
    (TM
    -0.07
    åĪĽéĢłçļĦ
    -0.07
    past
    -0.07
    à§ĩস
    -0.07
    ëĿ¼ëıĦ
    -0.07
    menin
    -0.07
     поÑģÑĤоÑĢон
    -0.07
    POSITIVE LOGITS
    elson
    0.07
    å¢
    0.07
     respectively
    0.07
    _del
    0.07
    å¦ĤæĦı
    0.07
    pired
    0.07
    unic
    0.07
    anic
    0.06
    ç³»åĪĹ
    0.06
    flutter
    0.06
    Activations Density 0.102%

    No Known Activations