© 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. 17336
    Prev
    Next
    INDEX
    Explanations

    know there or could be

    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
     ÙĨÛĮز
    -0.06
    Brief
    -0.06
    ä¸Ģ个åı«
    -0.06
    Äħ
    -0.06
    à¦Łà¦¿
    -0.06
     Downing
    -0.06
    没éĶĻ
    -0.06
    ÙĪغ
    -0.06
    à¦Łà¦¾
    -0.06
     kontr
    -0.06
    POSITIVE LOGITS
    åѦèĢĮ
    0.08
     somebody
    0.08
    è·Łäºº
    0.07
     Ñĥма
    0.07
    åī²
    0.07
    å¾Ĺæľī
    0.07
    人è¦ģ
    0.07
    ibro
    0.07
    人åı¯ä»¥
    0.07
     [<
    0.07
    Activations Density 0.093%

    No Known Activations