© 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. 22014
    Prev
    Next
    INDEX
    Explanations

    mathematical sets and transformations

    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
    ارÙĬ
    -0.07
    orts
    -0.07
    пад
    -0.07
    åį³ä½¿æĺ¯
    -0.06
    _ix
    -0.06
     Willi
    -0.06
    _pad
    -0.06
    ĶĦ
    -0.06
    SEQ
    -0.06
    rira
    -0.06
    POSITIVE LOGITS
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    0.10
    æľīä¸ĭåĪĹ
    0.08
    å´Ń
    0.08
    åħ·æľī以ä¸ĭ
    0.07
    ople
    0.07
    ple
    0.07
    满足
    0.07
    ä¼Ļ
    0.07
    à¸Ńà¸ģ
    0.07
    erness
    0.07
    Activations Density 0.061%

    No Known Activations