© 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. 29010
    Prev
    Next
    INDEX
    Explanations

    mathematical and logical symbols

    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
    rap
    -0.08
    tees
    -0.08
    çļĦéĤ£ä¸ª
    -0.07
    åľ¨éĤ£ä¸ª
    -0.07
    ÙĤÙħ
    -0.07
     embargo
    -0.07
     loin
    -0.07
    Ł
    -0.06
     prematurely
    -0.06
    èĦ¾æ°Ķ
    -0.06
    POSITIVE LOGITS
    å®ĥæĺ¯ä¸Ģç§į
    0.09
    ä¸Ģ个好
    0.09
    å®ĥæĺ¯ä¸Ģ个
    0.09
    elos
    0.09
    è¿Ļæĺ¯ä¸Ģ个
    0.08
    身为
    0.08
    —a
    0.08
    è¿Ļæĺ¯ä¸Ģ
    0.08
    ään
    0.08
    è¿Ļæĺ¯ä¸ª
    0.08
    Activations Density 0.050%

    No Known Activations