© 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. 11503
    Prev
    Next
    INDEX
    Explanations

    Figure numbers and web service names

    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
    à¸ĺรรมà¸Ĭาà¸ķิà¹ģละ
    -0.11
     nämlich
    -0.09
    สà¸Ļุà¸ģà¹ģละ
    -0.09
     à¤Ķर
    -0.09
    å°ĬéĩįåĴĮ
    -0.09
    交æµģä¸İ
    -0.09
    ë¶ĢìĻĢ
    -0.09
     and
    -0.09
    à¹ģละà¹Ģà¸Ľà¹ĩà¸Ļ
    -0.09
     и
    -0.09
    POSITIVE LOGITS
    /or
    0.23
     ê´Ģ볨íķĺìŬ
    0.14
     alike
    0.14
    /o
    0.14
    å¾Ģ常ä¸Ģæł·
    0.13
     sebagainya
    0.13
    /OR
    0.13
     importantly
    0.12
     ê´Ģ볨íķľ
    0.12
     lainnya
    0.12
    Activations Density 0.555%

    No Known Activations