© 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. 23810
    Prev
    Next
    INDEX
    Explanations

    origin and origins

    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
    stants
    -0.08
    iggins
    -0.07
    åľ¨åīįéĿ¢
    -0.07
    odore
    -0.07
    stät
    -0.07
     Disqus
    -0.07
    å¢ŀ
    -0.07
    ÙĪاء
    -0.07
     Scotia
    -0.06
    acters
    -0.06
    POSITIVE LOGITS
     пÑĢоиÑģÑħождениÑı
    0.12
     origins
    0.12
     origin
    0.11
     whence
    0.10
    æ¸ĬæºIJ
    0.10
    à¸ģำà¹Ģà¸Ļิà¸Ķ
    0.10
     возникновениÑı
    0.09
    -origin
    0.09
    origin
    0.09
    èµ·æºIJ
    0.09
    Activations Density 0.083%

    No Known Activations