© 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. 1959
    Prev
    Next
    INDEX
    Explanations

    initial conditions

    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
    ç¡®å®ŀæĺ¯
    -0.07
    chon
    -0.07
    人说
    -0.07
    åĶ¯ä¸Ģä¸Ģ个
    -0.06
    çļĦç¡®æĺ¯
    -0.06
    ä¸Ģåħ±æľī
    -0.06
    缴æİ¥ä¸İ
    -0.06
    æīİå®ŀåģļ好
    -0.06
    _THROW
    -0.06
    æĺ¯ä¸Ģ个éĿŀ常
    -0.06
    POSITIVE LOGITS
    å¾Ģå¾Ģ
    0.22
    å¾Ģå¾Ģæĺ¯
    0.20
     often
    0.20
     sometimes
    0.18
     possibly
    0.18
    ä¸įä¸Ģå®ļ
    0.18
     заÑĩаÑģÑĤÑĥÑİ
    0.18
     Often
    0.17
    Often
    0.17
    éĢļ常æĺ¯
    0.17
    Activations Density 0.589%

    No Known Activations