© 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. 26505
    Prev
    Next
    INDEX
    Explanations

    publication number and citation

    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
    èĩ
    -0.07
    è¿ĶãģĹ
    -0.07
    æīĢå¾Ĺ
    -0.07
    cho
    -0.07
    alp
    -0.06
     trance
    -0.06
    ebt
    -0.06
    angi
    -0.06
     trop
    -0.06
    缴å±ŀ
    -0.06
    POSITIVE LOGITS
    íĻķ
    0.07
     Easily
    0.07
     Fondazione
    0.07
    ãĥªãĤª
    0.07
     terc
    0.07
    åĽĽæº¢
    0.07
     ØŃÚ©
    0.07
    dech
    0.07
    Å¡Äį
    0.07
    åı¤ä»Ĭ
    0.06
    Activations Density 0.060%

    No Known Activations