© 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. 20911
    Prev
    Next
    INDEX
    Explanations

    Ghost of, Azkaban, Rose, Tower, House

    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
    ç¥Ģ
    -0.09
    æł¸å¿ĥä»·åĢ¼
    -0.07
    æŶèĩ³ä»ĬæĹ¥
    -0.06
    adari
    -0.06
    irable
    -0.06
    swagger
    -0.06
    端起
    -0.06
    åŁºçŁ³
    -0.06
    åĴ¬çīĻåĪĩ
    -0.06
    çĶŁåĮĸ
    -0.06
    POSITIVE LOGITS
    ÅŁti
    0.08
    æľīä¸Ģ次
    0.08
    缸å¤ĦçļĦ
    0.08
    δά
    0.08
    çļĦéĤ£ä¸ª
    0.08
    à¸Ĺัà¸Ķ
    0.07
    çĭ¬ä¸ĢæĹł
    0.07
    åĶ¯ä¸Ģä¸Ģ个
    0.07
    éĩĮéĿ¢æľī
    0.07
    izzi
    0.07
    Activations Density 0.004%

    No Known Activations