© 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. 8258
    Prev
    Next
    INDEX
    Explanations

    HTML table tags and list items

    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
    æľīä¸Ģé¢Ĺ
    -0.07
     manda
    -0.07
    ueue
    -0.07
    ##
    -0.06
     оÑĤо
    -0.06
    igure
    -0.06
    HR
    -0.06
    é¾Ļçľ¼
    -0.06
    æī©å±ķèµĦæĸĻ
    -0.06
    天马
    -0.06
    POSITIVE LOGITS
     rowspan
    0.07
    asilan
    0.07
    å£ķ
    0.07
    é¦ĸèµŀ
    0.07
    ertos
    0.07
    .EventHandler
    0.07
    渴æ±Ĥ
    0.06
    æ¡Ī件ä¸Ń
    0.06
    /hooks
    0.06
    ilig
    0.06
    Activations Density 0.017%

    No Known Activations