© 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. 31917
    Prev
    Next
    INDEX
    Explanations

    discussion of two items

    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
    allo
    -0.08
    رة
    -0.08
    AGMA
    -0.08
    oul
    -0.08
    ãģ¥ãģı
    -0.08
    uable
    -0.08
    oda
    -0.08
    canf
    -0.08
    ftp
    -0.08
    æĢ§åľ°
    -0.07
    POSITIVE LOGITS
     ÙĪبÙĬÙĨ
    0.07
    ,
    0.06
    assic
    0.06
    å¤ļæľĪ
    0.06
    ³
    0.06
     (
    0.06
    æĪĸå¤ļ个
    0.06
    ä»ĸ身ä¸Ĭ
    0.06
    جا
    0.06
    é¼İ
    0.06
    Activations Density 0.043%

    No Known Activations