© 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. 47274
    Prev
    Next
    INDEX
    Explanations

    inherent qualities and resources

    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
    éľĢè¦ģæł¹æį®
    -0.08
    åĨ³å®ļçĿĢ
    -0.08
    æł¹æį®ä½łçļĦ
    -0.08
     przyjÄĻ
    -0.08
    éľĢè¦ģèĢĥèĻij
    -0.07
    æĭħå½ĵèĢħ
    -0.07
    omia
    -0.07
    mdb
    -0.07
    èѦéĴŁ
    -0.07
    lesia
    -0.07
    POSITIVE LOGITS
    ãĤĴåĪ©çĶ¨ãģĹãģ¦
    0.13
    ä¼ĺåĬ¿
    0.13
    èµĦæºIJä¼ĺåĬ¿
    0.12
    为ä¾Ŀæīĺ
    0.11
     advantage
    0.11
    ä¿¡æģ¯è¿Ľè¡Į
    0.11
     leverage
    0.10
    并åĪ©çĶ¨
    0.10
    è¿Ļä¸ªæľºä¼ļ
    0.10
    çļĦä¼ĺåĬ¿
    0.10
    Activations Density 0.249%

    No Known Activations