© 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. 41890
    Prev
    Next
    INDEX
    Explanations

    clauses defining or describing what comes next

    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
    å¦Ĥæŀľä»ĸ们
    -0.07
    å¦ĤæŀľæĪij们
    -0.07
    åľ¨åĪ«äºº
    -0.07
    æĺ¯åIJ¦åľ¨
    -0.07
    å¦Ĥæŀľä»ĸ
    -0.06
    åģĩå¦Ĥ
    -0.06
    å¦Ĥæŀľèĩªå·±
    -0.06
     Americas
    -0.06
    å¦Ĥæŀľä½łæĺ¯
    -0.06
    éĿŀ常
    -0.06
    POSITIVE LOGITS
    åıĸèĢĮ代ä¹ĭ
    0.11
    çļĦä¸ĢåĪĩéĥ½
    0.11
    ä¸ĢåĪĩéĥ½
    0.11
    人被
    0.11
    ä¿¡æģ¯çĶ±
    0.10
     there
    0.10
    äºĭæħĭ
    0.09
    人们
    0.09
    她被
    0.09
    æĪij被
    0.09
    Activations Density 0.843%

    No Known Activations