© 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. 62439
    Prev
    Next
    INDEX
    Explanations

    one more time

    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
    aim
    -0.09
    ä¼Ĭå§ĭ
    -0.08
    第ä¸Ģ家
    -0.08
    é¦ĸå±Ĭ
    -0.08
    insky
    -0.07
    inker
    -0.07
    é¦ĸ个
    -0.07
    heen
    -0.07
     eerste
    -0.07
    çļĦ第ä¸ĢæŃ¥
    -0.07
    POSITIVE LOGITS
    æľĢåIJİä¸Ģ
    0.14
    æľĢåIJİçļĦ
    0.14
    æľĢåIJİä¸Ģ次
    0.13
    æľĢåIJİ
    0.12
     ë§Īì§Ģë§īìľ¼ë¡ľ
    0.12
    æľĢåIJİä¸Ģ个
    0.12
     remaining
    0.11
    æľĢå¾Įãģ«
    0.11
     آخرÛĮÙĨ
    0.11
    çļĦæľĢåIJİ
    0.11
    Activations Density 0.213%

    No Known Activations