© 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. 29888
    Prev
    Next
    INDEX
    Explanations

    common primary brain tumor

    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
    åħ¥ä¼į
    -0.08
    æľ¬é¢ĺçŃĶæ¡Ī
    -0.07
    ló
    -0.07
    çĭ¬ä¸ĢæĹłäºĮçļĦ
    -0.07
    ovah
    -0.07
    witz
    -0.07
    ë§Ŀ
    -0.07
    eko
    -0.06
    满æľĪ
    -0.06
    åĬ²
    -0.06
    POSITIVE LOGITS
    à¸Ĺาà¸ĩ
    0.09
     automotive
    0.08
    วà¸ĩà¸ģาร
    0.07
    ä¼ļåĬ¡
    0.07
    è¿ij代
    0.07
    aru
    0.07
    å®ĺåı¸
    0.07
     cryptographic
    0.07
    ç«ĻåĨħ
    0.07
    ä¸Ģå¸Ĩ
    0.06
    Activations Density 0.841%

    No Known Activations