© 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. 9537
    Prev
    Next
    INDEX
    Explanations

    numbers, series, range, or lists

    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
     sür
    -0.07
     вÑĭпÑĥÑģ
    -0.07
    ();)
    -0.07
    æĺ¯è¿Ļ个
    -0.07
     everywhere
    -0.07
     );
    -0.07
     dürfte
    -0.07
     ÙĦÙĦØ¥ÙĨ
    -0.07
    ä¸Ģéĩij
    -0.07
    让è¿Ļ个
    -0.07
    POSITIVE LOGITS
     specified
    0.08
     given
    0.07
     optionally
    0.07
    åī²
    0.07
    adas
    0.07
     Clarkson
    0.07
    æĮĩå®ļçļĦ
    0.06
    Pad
    0.06
    æĮĩå®ļ
    0.06
    åĩ¹åĩ¸
    0.06
    Activations Density 0.035%

    No Known Activations