© 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. 20676
    Prev
    Next
    INDEX
    Explanations

    divided into types

    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
    dbl
    -0.08
    atine
    -0.08
    alı
    -0.07
    éĽĨçļĦ
    -0.07
    bris
    -0.07
    ette
    -0.07
    çļĦä¸Ģ对
    -0.07
    æĽ´å¤ļä¿¡æģ¯
    -0.07
    çĻ¾ç±³
    -0.07
     Ving
    -0.07
    POSITIVE LOGITS
    两大类
    0.14
    主è¦ģåĪĨ为
    0.11
    åĪĨ为
    0.11
    åı¯åĪĨ为
    0.10
    åĪĨçĤº
    0.09
    两类
    0.09
    åı¯ä»¥åĪĨ为
    0.09
    两大
    0.08
    çļĦç§įç±»
    0.08
    åĪĴåĪĨ为
    0.08
    Activations Density 0.087%

    No Known Activations