© 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. 42698
    Prev
    Next
    INDEX
    Explanations

    monotonic increasing decreasing

    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
    LANG
    -0.10
    置身äºİ
    -0.09
    Xã
    -0.08
    天éķ¿
    -0.08
    emento
    -0.07
    éĩįéĩį
    -0.07
    ä¸īæĸ¹
    -0.07
    æĦıè§ģ书
    -0.07
    UBLIC
    -0.07
    erez
    -0.07
    POSITIVE LOGITS
    åįķè°ĥ
    0.11
     monot
    0.11
     increasing
    0.11
     decreasing
    0.10
    incre
    0.08
    Increasing
    0.08
    éĢĴåĩı
    0.08
    å¢ŀ
    0.08
    creasing
    0.08
     DECRE
    0.08
    Activations Density 0.003%

    No Known Activations