© 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. 24746
    Prev
    Next
    INDEX
    Explanations

    parts of things

    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
    oÅĽci
    -0.09
    æĢ»ä½ĵèĢĮè¨Ģ
    -0.08
    æīĢè°ĵ
    -0.08
    asel
    -0.07
    åŃIJäºĨ
    -0.07
    汶
    -0.07
    æķ´ä½ĵä¸Ĭ
    -0.07
    éĢĤåIJĪçļĦ
    -0.07
     vypl
    -0.07
    è¿ĻæŃ£æĺ¯
    -0.07
    POSITIVE LOGITS
    çļĦä¸ĢåĪĩéĥ½
    0.07
    åľ°åĿĢä½įäºİ
    0.07
    able
    0.07
    éģĵéķ¿
    0.07
    ä¹ĭéĹ´æľī
    0.06
    umis
    0.06
    åİĭåĬĽå¤§
    0.06
    uckles
    0.06
    ç«ŀäºīæ¿ĢçĥĪ
    0.06
    åĽ¾æĸ¯
    0.06
    Activations Density 0.178%

    No Known Activations