© 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. 23531
    Prev
    Next
    INDEX
    Explanations

    higher-order statistical terms

    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
    reja
    -0.07
    ujo
    -0.07
     Bravo
    -0.07
    çīĻ
    -0.07
    digit
    -0.07
    оÑģÑĤо
    -0.07
    achel
    -0.07
    è¯¥æľº
    -0.07
     Convention
    -0.07
    ooter
    -0.07
    POSITIVE LOGITS
    äºĮåįģäºĶ
    0.08
    æĸŁéħĮ
    0.07
    elan
    0.07
    udas
    0.07
    åĩºçİ°åľ¨äºĨ
    0.07
    äºĮåįģåħŃ
    0.07
    çĺ¸
    0.07
    iom
    0.06
    edia
    0.06
     إضاÙģ
    0.06
    Activations Density 0.002%

    No Known Activations