© 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. 1011
    Prev
    Next
    INDEX
    Explanations

    doi citations

    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
    Æ¡
    -0.07
    ted
    -0.07
    ovit
    -0.06
    unyi
    -0.06
    scher
    -0.06
    èĬĤèĬĤ
    -0.06
    漪
    -0.06
    оÑĤÑĮ
    -0.06
    oja
    -0.06
    ecker
    -0.06
    POSITIVE LOGITS
    檸
    0.08
     Burnett
    0.07
    è¦ģæĿ¥
    0.07
     ê·¸ëŀĺëıĦ
    0.07
    æĪij以åIJİ
    0.07
     >(
    0.07
    Ahead
    0.07
    ahl
    0.07
    ahr
    0.07
    elis
    0.07
    Activations Density 0.057%

    No Known Activations