© 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. 61974
    Prev
    Next
    INDEX
    Explanations

    undergoing elective surgery

    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
    æĢ¥
    -0.07
    ä¸ĸå¤ĸ
    -0.06
     stef
    -0.06
    åŃ¦ä¹łæĸ¹æ³ķ
    -0.06
    æ°¸è¿ľæĺ¯
    -0.06
    è¦ģéĿł
    -0.06
    追
    -0.06
    st
    -0.06
    deen
    -0.06
    abella
    -0.06
    POSITIVE LOGITS
    à¸Ńยูà¹Īà¹ģลà¹īว
    0.14
    顺便
    0.13
     already
    0.11
    éłĨ便
    0.11
    already
    0.11
    顺æīĭ
    0.10
     inadvertently
    0.10
    å·²ç»ıæľīäºĨ
    0.10
    å·²æľīçļĦ
    0.10
    å·²ç»ıæľī
    0.10
    Activations Density 0.511%

    No Known Activations