© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58860
    Prev
    Next
    INDEX
    Explanations

    comparing groups or separating things

    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
    кол
    -0.08
    åį¡è·¯
    -0.07
    awan
    -0.07
    æģ©æĸ¯
    -0.07
    и
    -0.06
    rade
    -0.06
    rad
    -0.06
    orb
    -0.06
    æ¯įåŃIJ
    -0.06
    osal
    -0.06
    POSITIVE LOGITS
     itself
    0.12
    Within
    0.12
     themselves
    0.11
    åĨħéĥ¨çļĦ
    0.11
    åĨħéĥ¨
    0.11
     Within
    0.11
    within
    0.10
    à¸Ķà¹īวยà¸ģัà¸Ļ
    0.10
    æľ¬èº«
    0.10
    ç»ĨåĪĨ
    0.10
    Activations Density 0.175%

    No Known Activations