© 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. 63297
    Prev
    Next
    INDEX
    Explanations

    registering, natural, combining, refolding, bug, impurities, blender, screen

    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
    çī
    -0.07
    uat
    -0.07
    æĺŃ
    -0.07
    à¥įन
    -0.07
    å¨ĵ
    -0.07
    _unsigned
    -0.07
    交éĢļ大åѦ
    -0.07
    åij¨ä¸Ģèĩ³
    -0.07
    าà¸Ĺ
    -0.07
    uhe
    -0.06
    POSITIVE LOGITS
     Alternatively
    0.15
    ìĿ´ê±°ëĤĺ
    0.15
     oppure
    0.15
    æĪĸéĢļè¿ĩ
    0.14
    æĪĸåľ¨
    0.14
    æĪĸèĢħæĺ¯
    0.13
    Alternatively
    0.13
    ê±°ëĤĺ
    0.13
    ãģĹãģŁãĤĬ
    0.13
    åıĪæĪĸèĢħ
    0.13
    Activations Density 0.397%

    No Known Activations