© 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. 37904
    Prev
    Next
    INDEX
    Explanations

    optional, array, object, hex

    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
    丢æİī
    -0.08
    å¿ĥæĢĿ
    -0.08
    ä¸įåĩº
    -0.08
    .forName
    -0.08
    OutOf
    -0.08
    æłĩè¯Ĩçłģ
    -0.08
    !=(
    -0.08
    alım
    -0.08
    äºĨ解ä¸Ģä¸ĭåIJ§
    -0.08
    _HEADERS
    -0.07
    POSITIVE LOGITS
    é¡»
    0.07
    ä¼łåħ¥
    0.07
     Ejem
    0.06
    ully
    0.06
    欲
    0.06
    -ish
    0.06
    æĿ¥è®²
    0.06
    ابÙĩ
    0.06
    å±ħ
    0.06
    .Must
    0.06
    Activations Density 0.100%

    No Known Activations