© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62666
    Prev
    Next
    INDEX
    Explanations

    historical study and personal experiences

    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
    åĮ»çĶŁè¯´
    -0.08
    æľī好çļĦ
    -0.08
    æľīæѤ
    -0.08
    çļĦåIJĦ
    -0.07
    åīįåºĶ
    -0.07
    ä¸ĢæŀĿ
    -0.07
     appropriate
    -0.07
     thereafter
    -0.07
    imbus
    -0.07
    åIJĦåŃ¦æł¡
    -0.07
    POSITIVE LOGITS
    ãģĹãģĭãĤĤ
    0.07
    akar
    0.07
    cca
    0.07
    ieu
    0.07
    à¹Ģà¸Īาะ
    0.07
    è½¬çľ¼éĹ´
    0.07
    åĨ·éŨ
    0.06
    çļĭ
    0.06
     ë³µíķ©
    0.06
    对æ¯Ķ
    0.06
    Activations Density 0.013%

    No Known Activations