© 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. 22029
    Prev
    Next
    INDEX
    Explanations

    key-value pairs (name, value)

    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
    ãģ£ãģĵ
    -0.07
    èµĦè´¨çļĦ
    -0.07
     dissip
    -0.07
    æĪijçļĦ人
    -0.06
     chees
    -0.06
     imper
    -0.06
     koti
    -0.06
     diss
    -0.06
     Rang
    -0.06
    arger
    -0.06
    POSITIVE LOGITS
    ä¸ĢæĿ¡é¾Ļ
    0.09
    ä¸ĭä¸ĢæĿ¡
    0.08
    fname
    0.08
    erta
    0.07
    ä¸Ģä½ĵ
    0.07
     istr
    0.07
    $o
    0.07
    ecome
    0.07
    ä»»ä½ķä¸ľè¥¿
    0.07
    éĵ¶å±±
    0.07
    Activations Density 0.005%

    No Known Activations