© 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. 29996
    Prev
    Next
    INDEX
    Explanations

    families & models

    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
    æį¢ä¸ª
    -0.07
    ä»
    -0.07
    åIJ±
    -0.06
    çķħ
    -0.06
    æį¢ä¸Ģ个
    -0.06
    ç¨ļ
    -0.06
    opp
    -0.06
    çĮĽ
    -0.06
    åķĦ
    -0.06
    ledge
    -0.06
    POSITIVE LOGITS
    æł¼æĭīæĸ¯
    0.09
    amilies
    0.08
    容纳
    0.08
    åı¦å¤ĸè¿ĺæľī
    0.08
    çļĦç»ĦåIJĪ
    0.08
    ç«ŀäºīæ¿ĢçĥĪ
    0.08
    社ä¼ļä¿¡çĶ¨ä»£çłģ
    0.08
    å¤ļè¾¾
    0.07
     blobs
    0.07
    anium
    0.07
    Activations Density 0.003%

    No Known Activations