© 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. 21491
    Prev
    Next
    INDEX
    Explanations

    competencies

    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
    æİĢ
    -0.07
    ä¸Ģ家ä¸īåı£
    -0.07
    æĺ¯ä¸ĢäºĽ
    -0.06
    æģ¢
    -0.06
    keur
    -0.06
     exploiting
    -0.06
     expuls
    -0.06
    icker
    -0.06
    ore
    -0.06
    rech
    -0.06
    POSITIVE LOGITS
    ä¹ĭä¸ĢçļĦ
    0.09
    ä¹ĭé¦ĸ
    0.09
    缺ä¸Ģä¸įåı¯
    0.09
    è¦ģç´ł
    0.08
    éĿ¢éĿ¢
    0.08
    俱åħ¨
    0.08
    对çĹĩä¸ĭèį¯
    0.08
    ucci
    0.08
    éļıæŶéļıåľ°
    0.07
    éĢIJä¸Ģ
    0.07
    Activations Density 0.109%

    No Known Activations