© 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. 16646
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with pi

    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
    ewise
    -0.07
    bek
    -0.07
    à¸Ĥà¹īาà¸ĩ
    -0.07
    lain
    -0.07
    eree
    -0.06
    å°ı说ç½ij
    -0.06
     каждаÑı
    -0.06
    åĽŀ羸
    -0.06
    æ¯ıåı°
    -0.06
    cwd
    -0.06
    POSITIVE LOGITS
    大åĪ°
    0.08
    Åijl
    0.07
    Vue
    0.07
    вала
    0.07
     infinity
    0.07
    .allowed
    0.07
    ä¸įéĻIJ
    0.07
    对称
    0.07
    å¤©æ±ł
    0.07
    iria
    0.06
    Activations Density 0.005%

    No Known Activations