© 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. 21408
    Prev
    Next
    INDEX
    Explanations

    Py factory complex

    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
    æľī以ä¸ĭ
    -0.08
    åħ·æľī以ä¸ĭ
    -0.08
    åħ·æľī丰å¯ĮçļĦ
    -0.08
    åħ·æľīå¾Īé«ĺçļĦ
    -0.07
    çŁŃæŶéĹ´
    -0.07
    åħ·æľīå¾Ī强çļĦ
    -0.07
    æĢ»ä½ĵä¸Ĭ
    -0.07
    åħ·æľīè¾ĥé«ĺçļĦ
    -0.07
    åħ·æľīä¸Ģå®ļçļĦ
    -0.07
    åħ·æľīä¸Ģå®ļ
    -0.07
    POSITIVE LOGITS
     effortlessly
    0.11
     meticulously
    0.11
     nestled
    0.10
     countless
    0.10
     beautifully
    0.10
     untouched
    0.09
     mighty
    0.09
    åľ¨è¿Ļçīĩ
    0.09
    åı¯ä¸įæĺ¯
    0.09
    ãģ¸ãģ¨
    0.09
    Activations Density 0.122%

    No Known Activations