© 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. 4363
    Prev
    Next
    INDEX
    Explanations

    numbers, letters, and symbols

    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
    ile
    -0.08
    åIJį
    -0.06
    çľ¨çľ¼
    -0.06
    agak
    -0.06
    an
    -0.06
    ori
    -0.06
    æ»ļæ»ļ
    -0.06
    ileo
    -0.06
    orc
    -0.06
    æ¯ıéĢ¢
    -0.06
    POSITIVE LOGITS
    _border
    0.09
    border
    0.08
    请èģĶç³»æĪij们
    0.08
    ارÙĩ
    0.08
    বাদ
    0.07
    Border
    0.07
     Ahok
    0.07
     kurie
    0.07
    аве
    0.07
    erialize
    0.07
    Activations Density 0.009%

    No Known Activations