© 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. 16931
    Prev
    Next
    INDEX
    Explanations

    starting word of a phrase

    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
    Âł
    -0.06
    人ä¸ĸ
    -0.06
    asser
    -0.06
     basic
    -0.06
     Estado
    -0.06
     spending
    -0.06
    æµħèī²
    -0.06
    轻信
    -0.06
    ç»ıæµİ社ä¼ļåıijå±ķçļĦ
    -0.05
    astia
    -0.05
    POSITIVE LOGITS
    NOP
    0.08
    æ½ľ
    0.08
    κοÏį
    0.08
    hlas
    0.08
    struments
    0.08
    èIJ½ä¸ĭ
    0.08
    USTA
    0.08
    ispers
    0.08
    OAD
    0.08
    UPLOAD
    0.08
    Activations Density 0.007%

    No Known Activations