© 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. 30002
    Prev
    Next
    INDEX
    Explanations

    parts

    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
    ä¸Ģ票
    -0.08
    angga
    -0.07
    _UTF
    -0.07
    stek
    -0.07
    é¡¿äºĨé¡¿
    -0.07
    quinas
    -0.07
    æ¨¡æł·
    -0.07
    tika
    -0.07
    sker
    -0.06
    ë¹Ļ
    -0.06
    POSITIVE LOGITS
     yes
    0.08
    yes
    0.07
     Yes
    0.07
    çķ¥
    0.07
    YES
    0.07
    ttp
    0.07
    åIJĮæĦıåIJİ
    0.07
    _strategy
    0.06
    æ½Ń
    0.06
    å½ĵå¿ĥ
    0.06
    Activations Density 0.001%

    No Known Activations