© 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. 61827
    Prev
    Next
    INDEX
    Explanations

    how something works

    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
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.08
    pose
    -0.07
    æĸ¹æ¡Ī
    -0.07
    æĸ¹æ¡ĪçļĦ
    -0.07
     INCLUDING
    -0.07
    orgia
    -0.07
    ç¥Ģ
    -0.07
    åIJĮæĹ¶å¯¹
    -0.07
    两ç§įæĸ¹å¼ı
    -0.07
    ä¹Łåı¯ä»¥æĺ¯
    -0.07
    POSITIVE LOGITS
    å°±çŁ¥éģĵäºĨ
    0.10
    åı¯çŁ¥
    0.10
    ãģĿãĤĤãģĿãĤĤ
    0.09
    å°±çŁ¥éģĵ
    0.08
    å°±ä¼ļåıijçİ°
    0.08
    æĪijä»¬çŁ¥éģĵ
    0.07
    ä¹ŁçŁ¥éģĵ
    0.07
    åĩ¡
    0.07
    éĥ½çŁ¥éģĵ
    0.06
    ä¸ĢèĪ¬æĿ¥è¯´
    0.06
    Activations Density 0.017%

    No Known Activations