© 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. 21273
    Prev
    Next
    INDEX
    Explanations

    powers and exponents

    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
    оеди
    -0.07
    гей
    -0.07
    ä½İçĿĢ头
    -0.06
    Kelu
    -0.06
    éļıåľ°
    -0.06
    ural
    -0.06
    æ³ī
    -0.06
    ä¸Ĭä¸ĭ游
    -0.06
    برة
    -0.06
    _lineno
    -0.06
    POSITIVE LOGITS
     powers
    0.09
     exponent
    0.09
    å¹Ĥ
    0.08
    .power
    0.08
    byn
    0.08
    /power
    0.07
    powers
    0.07
    妾
    0.07
    iation
    0.07
    vány
    0.07
    Activations Density 0.041%

    No Known Activations