© 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. 63152
    Prev
    Next
    INDEX
    Explanations

    numbers following 'the' or 'first word'

    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
    è¿Ļæł·åı¯ä»¥
    -0.08
    æĥ³çĿĢ
    -0.08
    è¿Ļæł·çļĦè¯Ŀ
    -0.07
     ës
    -0.07
    类似éĹ®é¢ĺ
    -0.07
    大åįİ
    -0.07
    æĥ³èijĹ
    -0.07
    è¿Ļæł·
    -0.07
    类似
    -0.07
    äºİæĺ¯ä»ĸ
    -0.07
    POSITIVE LOGITS
     unequiv
    0.07
     definit
    0.07
    å¿ħæľī
    0.07
    ä¸īæĹł
    0.06
    æ¨
    0.06
    otron
    0.06
    ilor
    0.06
    æĦıä¹īä¸ĬçļĦ
    0.06
    emas
    0.06
    ENN
    0.06
    Activations Density 0.002%

    No Known Activations