© 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. 20037
    Prev
    Next
    INDEX
    Explanations

    suffix

    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
    æİIJ
    -0.06
     subject
    -0.06
     Subject
    -0.06
    ç»ķ
    -0.06
    æ£Ģ
    -0.06
    æŀª
    -0.06
     merit
    -0.06
    aspers
    -0.06
    éĻ·
    -0.06
    èĨĽ
    -0.06
    POSITIVE LOGITS
    åIJİç¼Ģ
    0.10
    uffix
    0.09
    _suffix
    0.08
    suffix
    0.08
    æĸĩæľ«
    0.08
    移åĬ¨çīĪ
    0.08
     seme
    0.08
    edException
    0.08
    à¹Ĥà¸Ļ
    0.08
    Suffix
    0.08
    Activations Density 0.263%

    No Known Activations