© 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. 49052
    Prev
    Next
    INDEX
    Explanations

    code contexts

    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
    éºĴ
    -0.08
    à¯įà®ļ
    -0.08
    ti
    -0.08
    à¸ĩ
    -0.08
    etrics
    -0.07
    æŁł
    -0.07
    envir
    -0.07
    ç¡·
    -0.07
    į¨
    -0.07
    Ø©
    -0.07
    POSITIVE LOGITS
    ENTO
    0.06
    庶
    0.06
    ä¸įæ²»
    0.06
    åĴĮä¸ĭ
    0.06
    WindowText
    0.06
    è¿ĺæľīæľºä¼ļ
    0.06
     "
    0.06
    ienst
    0.06
    izer
    0.06
     Turning
    0.06
    Activations Density 0.003%

    No Known Activations