© 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. 14056
    Prev
    Next
    INDEX
    Explanations

    changes over time

    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
     using
    -0.07
     USING
    -0.07
    å¨ĺåŃIJ
    -0.07
    æīĭæľºéĺħ读
    -0.07
    >>>>>>>
    -0.07
     Using
    -0.07
    误导æĢ§éĻĪè¿°
    -0.06
    anjang
    -0.06
     гла
    -0.06
    è¨Ģæĥħ
    -0.06
    POSITIVE LOGITS
    æĪijåIJĹ
    0.09
    äºĨæķ´ä¸ª
    0.09
    å½¼æѤçļĦ
    0.09
     us
    0.08
     dirinya
    0.08
    å½¼æѤ
    0.08
     itself
    0.08
    idor
    0.08
    ä½łåij¢
    0.08
    人ãĤĴ
    0.07
    Activations Density 0.232%

    No Known Activations