© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39508
    Prev
    Next
    INDEX
    Explanations

    political or personal commitment

    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
    avana
    -0.07
    ä¸ĩåıĺ
    -0.07
    avan
    -0.07
    iedades
    -0.06
    undy
    -0.06
    åİĨåİĨ
    -0.06
    æĺ¨å¤ľ
    -0.06
    ava
    -0.06
    ä¸Ģ次次
    -0.06
    abaya
    -0.06
    POSITIVE LOGITS
    æĪIJ为ä¸ĢåIJį
    0.11
    并æĪIJ为
    0.10
    æŃ£å¼ı
    0.10
    æŃ£å¼ıçļĦ
    0.10
    并å¼Ģå§ĭ
    0.10
     permanently
    0.09
     forever
    0.09
    à¸Ńยà¹Īาà¸ĩà¹Ģà¸Ľà¹ĩà¸Ļà¸Ĺาà¸ĩà¸ģาร
    0.09
    ä»İæѤ
    0.09
    æ°¸ä¹ħ
    0.09
    Activations Density 0.553%

    No Known Activations