© 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. 25035
    Prev
    Next
    INDEX
    Explanations

    use followed by verbs or nouns

    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
    æĽ´å¤ļåĨħ容
    -0.09
    æĽ´å¤ļ精彩åĨħ容
    -0.08
    æīĢæľīåĨħ容
    -0.07
    ä»»ä½ķ人
    -0.07
    使çĶ¨åĴĮ
    -0.07
    ignes
    -0.07
    _queryset
    -0.07
    ëĮĢëĬĶ
    -0.06
    æĽ´å¤ļ精彩
    -0.06
    使çĶ¨çļĦæĺ¯
    -0.06
    POSITIVE LOGITS
    æŶéĹ´æĿ¥
    0.14
    ä»ĸæĿ¥
    0.11
    æŶéĹ´åİ»
    0.11
    éģĵæĿ¥
    0.11
     Äijá»ĥ
    0.10
     ÑĩÑĤобÑĭ
    0.09
    çļĦæĸ¹æ³ķæĿ¥
    0.09
    è¯ĿæĿ¥
    0.09
    çļĦæĸ¹å¼ıæĿ¥
    0.09
    以ä¸ĭæĸ¹å¼ı
    0.09
    Activations Density 0.167%

    No Known Activations