© 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. 49767
    Prev
    Next
    INDEX
    Explanations

    it's no secret

    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
     nanti
    -0.08
    éĢļè¿ĩ以ä¸Ĭ
    -0.08
     \`
    -0.08
     btw
    -0.08
    ä¹Łåı¯ä»¥åľ¨
    -0.08
    çľĭ好çļĦ
    -0.07
    .undo
    -0.07
    :_
    -0.07
    ä¹ŁæľīåĪ©äºİ
    -0.07
    éĿŀ常丰å¯Į
    -0.07
    POSITIVE LOGITS
    ä»Ĭ天å°ıç¼ĸ
    0.08
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    0.07
    å°ıç¼ĸ
    0.07
    ë§Įíģ¼
    0.07
    ä½łæĺ¯åIJ¦
    0.06
    è½¬çľ¼éĹ´
    0.06
    éĢ¢
    0.06
    âĢIJ
    0.06
    ä½łæľī没æľī
    0.06
    lobal
    0.06
    Activations Density 5.940%

    No Known Activations