© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2681
    Prev
    Next
    INDEX
    Explanations

    code structure and variables

    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
    ardin
    -0.07
    aus
    -0.07
    ç¿ħ
    -0.07
     Yug
    -0.07
    éģĵéķ¿
    -0.07
    æĻ´
    -0.07
    åĴĮæĿ¨
    -0.07
    inggu
    -0.06
    è¿İæĺ¥
    -0.06
    壤
    -0.06
    POSITIVE LOGITS
    æ¿Ģ
    0.08
    åIJĪåIJĮ约å®ļçļĦ
    0.07
    à¸ģ
    0.07
    #/
    0.07
    ä¸İæ²»çĸĹ
    0.06
    ulary
    0.06
    åIJijåħ¶
    0.06
    égr
    0.06
    éĶ¦ç»£
    0.06
    plevel
    0.06
    Activations Density 0.018%

    No Known Activations