© 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. 18990
    Prev
    Next
    INDEX
    Explanations

    color names, punctuation

    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
    éĻĨ游
    -0.08
    loge
    -0.08
    astia
    -0.08
    wirt
    -0.08
    ä¸įå®Į
    -0.07
    -tool
    -0.07
    ä¸įç»ı
    -0.07
    antly
    -0.07
    leit
    -0.07
    iola
    -0.07
    POSITIVE LOGITS
    ocht
    0.07
    ãģĦãģĭãģĮ
    0.07
    è»
    0.06
    ä»
    0.06
    ister
    0.06
     tslint
    0.06
    åıįé¦ĪæĦıè§ģ
    0.06
    à¸Īุ
    0.06
    arching
    0.06
    è¿Ļæł·çļĦè¯Ŀ
    0.06
    Activations Density 0.001%

    No Known Activations