© 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. 19220
    Prev
    Next
    INDEX
    Explanations

    font family, scale lengths, muscle fatigue, TP levels, vital materialism

    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
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.11
    æĪĸèĢħåħ¶ä»ĸ
    -0.09
    _EXIST
    -0.08
    /etc
    -0.07
    uant
    -0.07
    æĪĸåħ¶
    -0.07
    ãĥ¤
    -0.07
    cian
    -0.07
    æĪĸåħ¶ä»ĸ
    -0.07
    ToDate
    -0.07
    POSITIVE LOGITS
     AND
    0.09
    æĢ§åĴĮ
    0.08
    åĴĮ
    0.07
    åIJĮæŶå°Ĩ
    0.07
    éĹ®é¢ĺåĴĮ
    0.07
    åĽºçĦ¶
    0.07
    éĥ¨åĴĮ
    0.07
    åĴĮ对
    0.07
    åĴĮä¸Ģ个
    0.07
    ãĢįãĢĮ
    0.07
    Activations Density 0.134%

    No Known Activations