© 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. 25733
    Prev
    Next
    INDEX
    Explanations

    realized I, realized that

    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¿Ŀè¯ģåħ¶
    -0.07
    æĪij们å¸ĮæľĽ
    -0.07
    举个ä¾ĭåŃIJ
    -0.07
    æĪijä»¬çĽ¸ä¿¡
    -0.06
    Screenshot
    -0.06
    举个
    -0.06
    immy
    -0.06
    ä»ij
    -0.06
    zor
    -0.06
    å¸ĮæľĽåı¯ä»¥
    -0.06
    POSITIVE LOGITS
    åİŁæĿ¥æĺ¯
    0.13
    æĢªä¸įå¾Ĺ
    0.13
    åİŁæĿ¥
    0.12
    åİŁä¾Ĩ
    0.12
     ternyata
    0.11
    éļ¾æĢª
    0.11
    æģįçĦ¶å¤§æĤŁ
    0.11
    æŀľçĦ¶
    0.10
    æŀľçĦ¶æĺ¯
    0.10
     previously
    0.10
    Activations Density 0.287%

    No Known Activations