© 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. 49713
    Prev
    Next
    INDEX
    Explanations

    that is

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.11
    ity
    -0.08
    eature
    -0.08
    artal
    -0.08
    anitize
    -0.08
    éĤ£åı¯
    -0.07
    à¥ĩ
    -0.07
    ت
    -0.07
    ãģŁãĤģ
    -0.07
     ë¶Ī구íķĺê³ł
    -0.07
    POSITIVE LOGITS
    สà¹Į
    0.09
    iness
    0.08
    å°Ķ
    0.08
    à¹Ĩ
    0.08
    æĺ¯ä¸ĢåĪĩ
    0.07
    fully
    0.07
    istos
    0.07
    ä¸Ģæĸ°
    0.07
    zelfde
    0.07
    裡çļĦ
    0.07
    Activations Density 0.038%

    No Known Activations