© 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. 17415
    Prev
    Next
    INDEX
    Explanations

    perspectives, viewpoints, concerns, desires

    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
    åĤ¬äºº
    -0.09
    æį¢æĿ¥
    -0.08
    åİĨåı²ä¿¡æģ¯
    -0.08
    arring
    -0.08
    æĦŁäººçļĦ
    -0.08
    æĦŁäºº
    -0.07
    å¼ķ人åħ¥èĥľ
    -0.07
    åĴĮæĦıä¹ī
    -0.07
    æĺłåħ¥çľ¼å¸ĺ
    -0.07
    ä¸į容忽è§Ĩ
    -0.07
    POSITIVE LOGITS
     views
    0.10
     view
    0.09
    对æĸ°
    0.09
     desire
    0.09
    认为
    0.09
     regard
    0.09
     understanding
    0.09
    认å®ļ
    0.08
    对该
    0.08
    åĪĻ认为
    0.08
    Activations Density 0.542%

    No Known Activations