© 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. 1099
    Prev
    Next
    INDEX
    Explanations

    combinations or specifications

    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
    大éĩij
    -0.08
    åĴĮæľīåħ³
    -0.07
    czyk
    -0.07
    iep
    -0.07
    pec
    -0.07
    UES
    -0.07
    åĴĮèĩªå·±çļĦ
    -0.07
    aces
    -0.07
    并对åħ¶
    -0.07
    æľĿ天
    -0.07
    POSITIVE LOGITS
     serta
    0.09
    ãģ¨ãģĦãģ£ãģŁ
    0.09
    æŀĦæĪIJçļĦ
    0.08
    conditions
    0.08
     sowie
    0.07
    ãģĦãģ£ãģŁ
    0.07
     conditions
    0.07
    atica
    0.07
    è¿ĻäºĽæķ°æį®
    0.07
    eds
    0.06
    Activations Density 0.515%

    No Known Activations