© 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. 56140
    Prev
    Next
    INDEX
    Explanations

    listing conjunctions and actions

    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
    åĽŀåĪ°äºĨ
    -0.08
    æĦıè¯ĨåĪ°äºĨ
    -0.08
    ä¼ļ被
    -0.07
    认è¯ĨåĪ°äºĨ
    -0.07
    ä¸Ń
    -0.07
    åı¯ä»¥è¢«
    -0.07
    åijĬè¯īäºĨ
    -0.07
    ç»ıè¿ĩäºĨ
    -0.07
     happening
    -0.07
    æĭ¿åĪ°äºĨ
    -0.07
    POSITIVE LOGITS
    并对
    0.11
    åģļäºĽ
    0.10
    å¹¶åľ¨
    0.10
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    0.10
    并ä»İ
    0.10
    并æıIJä¾Ľ
    0.09
    并为
    0.09
    并éĢļè¿ĩ
    0.09
    åĪĽéĢłä¸Ģ个
    0.09
    åģļä¸ĢäºĽ
    0.09
    Activations Density 0.457%

    No Known Activations