© 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. 45809
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

    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
    ÙĪرÛĮ
    -0.07
    éĢĥåĩº
    -0.07
    arka
    -0.07
     tricks
    -0.07
    è¿Ļæł·æīįèĥ½
    -0.07
    лиÑĤ
    -0.07
    æ¡¥éķĩ
    -0.06
    ueva
    -0.06
     квиÑĤ
    -0.06
     intimate
    -0.06
    POSITIVE LOGITS
    åıªè¦ģèĥ½
    0.09
    åı¯ä»¥çļĦ
    0.08
    çħ§æł·
    0.08
     nonetheless
    0.08
    è¿ĺæĺ¯åı¯ä»¥
    0.08
    åıªä¸įè¿ĩ
    0.08
    ä¸įå½±åĵį
    0.08
     طاÙĦ
    0.08
    没æľīéĹ®é¢ĺ
    0.08
    åıªæĺ¯
    0.08
    Activations Density 0.059%

    No Known Activations