© 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. 23916
    Prev
    Next
    INDEX
    Explanations

    option="key="

    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
    ella
    -0.08
    ä½łäºĨ
    -0.08
    人äºĨ
    -0.07
    elu
    -0.07
     Giunta
    -0.07
     getResult
    -0.07
    åŃĺ
    -0.07
    ().'
    -0.07
    她äºĨ
    -0.06
    ()",
    -0.06
    POSITIVE LOGITS
    DateFormat
    0.08
    æľĢåħ³éĶ®
    0.07
     ComVisible
    0.07
    NumberOf
    0.07
    .TryParse
    0.07
    æĢ»
    0.07
    æ»ļæ»ļ
    0.07
    ÙĬرÙĪ
    0.06
    人åĿĩ
    0.06
    ç¼ļ
    0.06
    Activations Density 0.200%

    No Known Activations