© 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. 32073
    Prev
    Next
    INDEX
    Explanations

    programming and math concepts

    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
    arau
    -0.08
    ä¿¡æģ¯åıĬ
    -0.07
    íį¼
    -0.07
    åľ¨åģļ
    -0.07
    åŁºæľ¬æĿ¡ä»¶
    -0.07
    razio
    -0.07
    éģ¿
    -0.07
    å°Ķé¡¿
    -0.06
    overs
    -0.06
    anos
    -0.06
    POSITIVE LOGITS
    ahan
    0.08
    éĻĦåĬł
    0.07
    ä¸įè¿ĩæĿ¥
    0.07
    è¿ĩæĿ¥
    0.07
    celet
    0.07
    çij¾
    0.07
    æĽ´ç²¾å½©
    0.07
    èĬľ
    0.07
    鼻åŃIJåł±
    0.07
    ีà¹Īยà¹Į
    0.07
    Activations Density 0.003%

    No Known Activations