© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22762
    Prev
    Next
    INDEX
    Explanations

    questions and phrases

    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
    criptors
    -0.07
    ocl
    -0.07
    ĻĤ
    -0.07
    /terms
    -0.07
    ä¸įåĸĦ
    -0.07
    ä¸įæĹ©
    -0.07
    纳西
    -0.07
     //!<
    -0.07
    ieee
    -0.07
    ç´¢
    -0.06
    POSITIVE LOGITS
    ioned
    0.09
    wend
    0.07
    çłĶ究ä¼ļ
    0.07
    å¾Ĺä¸Ĭ
    0.06
    åĬłæ²¹
    0.06
    ewel
    0.06
    .reload
    0.06
    è¿ĻæŶ
    0.06
    å¥Ĺè·¯
    0.06
    ä¹ĭç±»çļĦ
    0.06
    Activations Density 0.015%

    No Known Activations