© 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. 8885
    Prev
    Next
    INDEX
    Explanations

    point of integrity

    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
    rash
    -0.07
    æĥ³è±¡
    -0.07
    èĩªå¾Ĺ
    -0.07
    æѦ
    -0.07
    gether
    -0.07
    DEFINE
    -0.06
    æľīä¸ĭåĪĹ
    -0.06
    IONES
    -0.06
    æľīä¸įåIJĮçļĦ
    -0.06
    arani
    -0.06
    POSITIVE LOGITS
     namely
    0.13
    nam
    0.11
     yaitu
    0.10
    éĤ£å°±æĺ¯
    0.09
     nemlig
    0.09
     nämlich
    0.09
     namelijk
    0.09
    Nam
    0.08
     Nam
    0.08
    èİ«è¿ĩäºİ
    0.08
    Activations Density 0.174%

    No Known Activations