© 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. 10456
    Prev
    Next
    INDEX
    Explanations

    time and place names

    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
    tees
    -0.08
    emons
    -0.07
    à·Ģà·ı
    -0.07
    æĢ»æ¯Ķ
    -0.07
    åıªç®¡
    -0.07
    åı¯åĸľ
    -0.07
    ÑİÑĢа
    -0.07
    çĪ±ä¸ĬäºĨ
    -0.07
    moto
    -0.07
    entai
    -0.07
    POSITIVE LOGITS
    æĪĸåħ¶ä»ĸ
    0.07
    æĤ£
    0.07
    令
    0.07
    ç®Ĺ
    0.06
    andard
    0.06
    æłĩåĩĨ
    0.06
    ä¸Ģ票
    0.06
    家æķĻ
    0.06
    arin
    0.06
    大äºĭ
    0.06
    Activations Density 0.021%

    No Known Activations