© 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. 7367
    Prev
    Next
    INDEX
    Explanations

    instructions below

    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
    ufr
    -0.09
    ä»ķæĸ¹
    -0.07
    yai
    -0.07
    æŶéĹ´éĩĮ
    -0.07
    PASS
    -0.06
    ille
    -0.06
     ofs
    -0.06
    ältä
    -0.06
    _prec
    -0.06
    ä¹ĭ乡
    -0.06
    POSITIVE LOGITS
     Äijá»ĥ
    0.20
     ÑĩÑĤобÑĭ
    0.18
    à¹Ģà¸ŀืà¹Īà¸Ń
    0.15
    æĸ¹æ³ķæĿ¥
    0.13
    Äijá»ĥ
    0.13
     ÑĩÑĤоб
    0.13
     ׼×ĵ×Ļ
    0.13
     Ñīоб
    0.12
    æĺ¯ä¸ºäºĨ
    0.11
     à¹Ģà¸ŀืà¹Īà¸Ń
    0.11
    Activations Density 0.651%

    No Known Activations