© 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. 64990
    Prev
    Next
    INDEX
    Explanations

    dependencies and properties

    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
    ç¼ħ
    -0.07
    avanaugh
    -0.07
    æī§è¡Į
    -0.07
    mann
    -0.07
    sville
    -0.07
    ingly
    -0.07
    çļĻ
    -0.07
    eviÄĩ
    -0.07
    sWith
    -0.07
    æijĩ篮
    -0.06
    POSITIVE LOGITS
    ç´¢
    0.07
    çĭ
    0.07
     Bari
    0.07
    å¦Ĥä¸ĭ
    0.06
    é¨
    0.06
     ÑĦиг
    0.06
     componenti
    0.06
    å¦ĤåĽ¾
    0.06
    .velocity
    0.06
    äch
    0.06
    Activations Density 0.001%

    No Known Activations