© 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. 32557
    Prev
    Next
    INDEX
    Explanations

    impact or capture

    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
    æ°ijåĪĿ
    -0.08
    ãĥĩãĤ£ãĥ³ãĤ°
    -0.07
    iin
    -0.07
    spel
    -0.07
    abar
    -0.07
    _dst
    -0.07
    âĢ¥
    -0.07
    榴
    -0.06
     Âł Âł Âł Âł
    -0.06
    pps
    -0.06
    POSITIVE LOGITS
    æĽ¸è¨ĺ
    0.07
    ãģĦãĤī
    0.06
     ëĶ°
    0.06
    æĺ¯ä¸Ģ缴
    0.06
    iciar
    0.06
    umat
    0.06
    驻马
    0.06
    ÙĦس
    0.06
    ateg
    0.06
    hu
    0.06
    Activations Density 0.020%

    No Known Activations