© 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. 28808
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or punctuation

    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
    trys
    -0.08
    jured
    -0.08
    eses
    -0.08
     برا
    -0.07
    Matcher
    -0.07
    èĢĮéļıçĿĢ
    -0.07
    çļĦ人äºĨ
    -0.07
    è©°ãĤģ
    -0.07
     quantify
    -0.07
    èĥİ
    -0.07
    POSITIVE LOGITS
    нÑij
    0.07
    åĨ·æļĸ
    0.07
     meaning
    0.07
    ä¸ī次
    0.07
    satz
    0.07
    è¿ĻæĦıåij³çĿĢ
    0.06
    ushi
    0.06
     Kramer
    0.06
    ourmet
    0.06
    æĦıåij³çĿĢ
    0.06
    Activations Density 0.018%

    No Known Activations