© 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. 12512
    Prev
    Next
    INDEX
    Explanations

    special characters or punctuation

    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
    çļĨ为
    -0.07
    ero
    -0.07
     Zam
    -0.06
    åĬ©äºİ
    -0.06
    #print
    -0.06
    è¿ijå¹³
    -0.06
    )**,
    -0.06
    âĢ¦*
    -0.06
     Clo
    -0.06
    .now
    -0.06
    POSITIVE LOGITS
    æĪ·æĪ·
    0.07
    æĸ°åĬłåĿ¡
    0.07
     dear
    0.07
    aversal
    0.07
    è§ģ人
    0.07
    æ´»
    0.07
    uess
    0.07
     Attacks
    0.07
    AspectRatio
    0.07
    ç½ijç«Ļ导èĪª
    0.07
    Activations Density 0.234%

    No Known Activations