© 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. 51576
    Prev
    Next
    INDEX
    Explanations

    masked bodies, controlled lighting, skin rejuvenation

    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
    æĪĴ
    -0.07
    arto
    -0.06
    ãģĵãģ¨ãĤĦ
    -0.06
    oooooooo
    -0.06
    ething
    -0.06
    æķĪæŀľåĴĮ
    -0.06
    æ¯ĵ
    -0.06
     nämlich
    -0.06
    AGMA
    -0.06
    à¸ĺรรมà¸Ĭาà¸ķิà¹ģละ
    -0.06
    POSITIVE LOGITS
    æ³ķçŃī
    0.15
    æ´»åĬ¨çŃī
    0.15
    管çIJĨçŃī
    0.14
    æĬĢæľ¯çŃī
    0.13
    ä¸Ńå¿ĥçŃī
    0.13
     etc
    0.13
    çŃīçŃī
    0.13
    ä¿¡æģ¯çŃī
    0.13
    设å¤ĩçŃī
    0.13
    å·¥ç¨ĭçŃī
    0.12
    Activations Density 0.405%

    No Known Activations