© 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. 32153
    Prev
    Next
    INDEX
    Explanations

    path components and version numbers

    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
     Freed
    -0.07
    æ¯ıéļĶ
    -0.06
    èĤ¡ä¸ľåıĬ
    -0.06
    ä¸Ģè¾ĪåŃIJ
    -0.06
    AGAIN
    -0.06
     Kecil
    -0.06
    æĪĸ个人
    -0.06
    èħĬ
    -0.06
     dụng
    -0.06
    å®ļæľŁçļĦãģ«
    -0.06
    POSITIVE LOGITS
    æľŁçļĦ
    0.09
    _APB
    0.08
    å¤į
    0.08
     óta
    0.08
    æľŁ
    0.08
    astia
    0.08
    -era
    0.08
    è¿ĩåIJİ
    0.08
    ForObject
    0.08
    EDIA
    0.08
    Activations Density 0.038%

    No Known Activations