© 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. 39817
    Prev
    Next
    INDEX
    Explanations

    etc., usw., itd

    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
    é¢ĦæľŁ
    -0.06
    umin
    -0.06
    iras
    -0.06
     pled
    -0.06
    åºı
    -0.06
    explained
    -0.06
    macros
    -0.06
     isize
    -0.06
    ��
    -0.06
    ấn
    -0.06
    POSITIVE LOGITS
    çŃīçŃī
    0.14
     etc
    0.13
    è¿ĻäºĽéĥ½
    0.11
     usw
    0.10
    etc
    0.10
    æĥħåĨµçŃī
    0.09
    æ´»åĬ¨çŃī
    0.09
    以åıĬåIJĦç§į
    0.09
     itd
    0.09
    ä¿¡æģ¯çŃī
    0.08
    Activations Density 0.001%

    No Known Activations