© 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. 33845
    Prev
    Next
    INDEX
    Explanations

    deficiencies and disorders

    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
    anco
    -0.09
    ianti
    -0.07
    æĺŃ
    -0.07
    obe
    -0.06
    ç¨ĭ度ä¸Ĭ
    -0.06
    ous
    -0.06
    говоÑĢ
    -0.06
    oret
    -0.06
    ä¸įå¤ļçļĦ
    -0.06
     usus
    -0.06
    POSITIVE LOGITS
     problems
    0.10
    éĹ®é¢ĺæŶ
    0.10
    失
    0.10
     пÑĢоблемÑĭ
    0.09
    ä¸ĬçļĦ
    0.09
     difficulties
    0.09
    éĹ®é¢ĺåĴĮ
    0.09
    æĸ¹éĿ¢çļĦéĹ®é¢ĺ
    0.09
     loss
    0.09
    éĹ®é¢ĺ
    0.09
    Activations Density 0.501%

    No Known Activations