© 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. 51694
    Prev
    Next
    INDEX
    Explanations

    trivial cases, functions, solutions

    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
    æłĩè®°
    -0.07
     Strategic
    -0.07
    è¿Ļ座
    -0.07
    é¾ĻéŨ
    -0.06
     calculated
    -0.06
     Equity
    -0.06
    ä¸įå°ıäºİ
    -0.06
    ç²¾æĺİ
    -0.06
    sker
    -0.06
    ance
    -0.06
    POSITIVE LOGITS
     solutions
    0.11
     Solutions
    0.08
     tron
    0.08
    Nil
    0.08
    çļĦåŃĺåľ¨
    0.08
    Null
    0.08
     addChild
    0.08
     Lösungen
    0.08
     Fourier
    0.07
     ÑĢеÑĪений
    0.07
    Activations Density 0.008%

    No Known Activations