© 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. 33280
    Prev
    Next
    INDEX
    Explanations

    Maltese 'ais', 'air', 'aur', 'Kais'

    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
    ×IJ×ķת
    -0.08
    ë¦ĩ
    -0.08
    باع
    -0.08
    ãģĨãģĪ
    -0.08
    عاÙħÙĦ
    -0.08
    æĪij为群ä¼ĹåĬŀå®ŀäºĭ
    -0.07
    اعت
    -0.07
    ëĤĺë§Ī
    -0.07
    дÑĸй
    -0.07
    ateur
    -0.07
    POSITIVE LOGITS
    0.12
    à¸Ĺà¹Į
    0.09
    ลà¹Į
    0.09
    à¹Į
    0.09
    enticator
    0.09
    ãģ¾ãģĹãģ¦
    0.08
     trúc
    0.08
    áĥłáĥĿ
    0.08
    ician
    0.08
    erness
    0.08
    Activations Density 1.806%

    No Known Activations