© 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. 42707
    Prev
    Next
    INDEX
    Explanations

    section headings

    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
    sä
    -0.08
    ektor
    -0.07
    å¹³æ¹ĸ
    -0.07
    iht
    -0.07
    åĪĨåĪ«æĺ¯
    -0.07
    rafa
    -0.06
    ********************
    -0.06
     Relax
    -0.06
    ****************************
    -0.06
    ä½łä¸Ģ
    -0.06
    POSITIVE LOGITS
    对åĨ²
    0.07
    ryn
    0.07
     Panas
    0.07
    imore
    0.07
    ä¸į为人
    0.07
    åģ¥åĦ¿
    0.07
    æĪĺçķ¥æĢ§
    0.07
    ä¸įæ¯Ķ
    0.06
    ailing
    0.06
    æĤ´
    0.06
    Activations Density 0.017%

    No Known Activations