© 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. 32843
    Prev
    Next
    INDEX
    Explanations

    miscellaneous items

    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
    ä¹Łå¥½
    -0.06
    å¨ĺåŃIJ
    -0.06
    1
    -0.06
    aney
    -0.06
    åѵ
    -0.06
    æĺ¥æļĸ
    -0.06
    hoff
    -0.06
    à¹Ģลีà¹īยà¸ĩ
    -0.06
     lun
    -0.05
    没æľī
    -0.05
    POSITIVE LOGITS
    ãģĿãģ®ä»ĸ
    0.09
     Miscellaneous
    0.09
     miscellaneous
    0.09
    )':
    0.09
    )":
    0.08
    管çIJĨåıĬ
    0.08
    æŶéĹ´åıĬ
    0.08
    æĽ´åı¯
    0.08
    管çIJĨæĸ¹éĿ¢
    0.08
     ãģĿãģ®ä»ĸ
    0.08
    Activations Density 0.013%

    No Known Activations