© 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. 32255
    Prev
    Next
    INDEX
    Explanations

    lists including examples and explanations

    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
    人æĹł
    -0.08
    è¿Ļä¸ĢçĤ¹
    -0.07
    lig
    -0.07
    мÑĸн
    -0.07
    orth
    -0.07
    该åİ¿
    -0.06
    ful
    -0.06
    amil
    -0.06
    è¿ĻçĤ¹
    -0.06
    嫦
    -0.06
    POSITIVE LOGITS
    åīįèĢħ
    0.15
     respectively
    0.14
    åĪĨåĪ«
    0.12
    åĪĨåĪ«ä¸İ
    0.12
     ê°ģê°ģ
    0.12
    åIJĦèĩªçļĦ
    0.12
    ãģĿãĤĮãģŀãĤĮ
    0.12
    ãģ©ãģ¡ãĤīãĤĤ
    0.12
    åIJĦèĩª
    0.11
     alike
    0.11
    Activations Density 0.179%

    No Known Activations