© 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. 46425
    Prev
    Next
    INDEX
    Explanations

    answer starters

    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
    عدÙħ
    -0.07
    artes
    -0.07
    ighbors
    -0.07
    /errors
    -0.07
    lbrace
    -0.07
    (er
    -0.07
    {return
    -0.07
    ilers
    -0.07
    idang
    -0.06
    {@
    -0.06
    POSITIVE LOGITS
    bia
    0.07
    ç¯ĩä¸Ģ
    0.07
    ikum
    0.07
     âĢ¢
    0.07
    olle
    0.07
    ãĥ£
    0.07
     âĸª
    0.06
    landen
    0.06
    è¿Ļéĥ¨åĪĨ
    0.06
    年头
    0.06
    Activations Density 0.167%

    No Known Activations