© 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. 20052
    Prev
    Next
    INDEX
    Explanations

    coordinates, location, date, income, data

    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
    /cards
    -0.08
    odaw
    -0.08
     alike
    -0.08
    ãģ«éĻIJ
    -0.08
    .setter
    -0.08
    çľĭä¼¼
    -0.07
    èĢĮå·²
    -0.07
     dalje
    -0.07
    /testing
    -0.07
    èĢĮæĿ¥
    -0.07
    POSITIVE LOGITS
    并ä»İ
    0.09
    并å°Ĩåħ¶
    0.09
    å¹¶æł¹æį®
    0.08
    并åIJij
    0.08
    并å¼Ģå§ĭ
    0.08
    并æĮīçħ§
    0.08
    并积æŀģ
    0.08
    并ç»Ħç»ĩ
    0.07
    æĥħåĨµåIJİ
    0.07
     بÙĨاء
    0.07
    Activations Density 0.068%

    No Known Activations