© 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. 1530
    Prev
    Next
    INDEX
    Explanations

    questions ending in question marks

    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
    èĬĻ
    -0.08
    æīĢ欲
    -0.07
    oÄį
    -0.07
     íĸĪê³ł
    -0.07
    rok
    -0.07
    .insertBefore
    -0.07
    orar
    -0.07
    opat
    -0.07
    ÙĪاج
    -0.07
    åįģå¹´æĿ¥
    -0.07
    POSITIVE LOGITS
    è¿Ļ两
    0.08
    è¿Ļ两个
    0.07
    两èĢħ
    0.07
    åĪ°è¿ĩ
    0.07
    åIJİèĢħ
    0.07
    åıĮèĬĤ
    0.06
    رب
    0.06
     Serta
    0.06
     serta
    0.06
    两ä¸į误
    0.06
    Activations Density 0.198%

    No Known Activations