© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48506
    Prev
    Next
    INDEX
    Explanations

    reunion, infrastructure, speed, alone, role

    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
     approximately
    -0.07
    figure
    -0.07
     wrongly
    -0.06
    饱
    -0.06
     falsely
    -0.06
     almost
    -0.06
    åįĵ
    -0.06
    βά
    -0.06
    åĴĮ社ä¼ļåıijå±ķ
    -0.06
     assolutamente
    -0.06
    POSITIVE LOGITS
    ä¹Łä¸į太
    0.09
    ä¸įå¦Ĥ
    0.09
    ãģĹãĤĤ
    0.09
    ëĿ½
    0.08
    èĢĮæĺ¯ä¸Ģ个
    0.08
    ibaldi
    0.08
    ä¹Łæľªå¿ħ
    0.08
    èĢĮæĺ¯è¦ģ
    0.08
    ä¹Łä¸įä¸Ģå®ļ
    0.08
    æľīæŶä¼ļ
    0.08
    Activations Density 0.087%

    No Known Activations