© 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. 30884
    Prev
    Next
    INDEX
    Explanations

    sequence punctuation

    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
    微信åħ¬ä¼Ĺå¹³åı°
    -0.08
    ouv
    -0.08
    itto
    -0.07
    à¸łà¸²à¸¢à¸«à¸¥à¸±à¸ĩ
    -0.07
    cind
    -0.07
    nock
    -0.07
    åħĪçĶ¨
    -0.07
    ä¸Ģå¹ķ
    -0.07
    çİĩ
    -0.07
     ëŀĺ
    -0.07
    POSITIVE LOGITS
    è¿ĻæĦıåij³çĿĢ
    0.07
    ä¹Łå°±æĺ¯è¯´
    0.07
    åIJ¾
    0.07
    ä¹Łå°±æĦıåij³çĿĢ
    0.07
    è¿Ļ对äºİ
    0.07
    ä¹Łå°±
    0.07
    ä¸ĢçŃī
    0.06
    æĦıåij³çĿĢ
    0.06
    åį³
    0.06
    åİŁä½į
    0.06
    Activations Density 0.033%

    No Known Activations