© 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. 33570
    Prev
    Next
    INDEX
    Explanations

    depending on choice

    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
    endt
    -0.09
    æĪĸèĢħ说
    -0.08
    ãĤĦãģı
    -0.08
    à¹ģละà¸Ħวาม
    -0.07
     Tám
    -0.07
    uiltin
    -0.07
    abo
    -0.07
    ucch
    -0.07
    edef
    -0.07
    owitz
    -0.06
    POSITIVE LOGITS
     depending
    0.15
    depending
    0.14
     alike
    0.12
     whichever
    0.12
     respectively
    0.11
    åıĸåĨ³äºİ
    0.11
     dependendo
    0.11
    æĢ»ä¹ĭ
    0.10
     dependiendo
    0.10
    ãģĦãģļãĤĮ
    0.09
    Activations Density 0.342%

    No Known Activations