© 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. 10697
    Prev
    Next
    INDEX
    Explanations

    city 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
    ä¸Ĭ大
    -0.07
    ogue
    -0.07
    è·¯ä¸İ
    -0.07
    ä¸įä¸İ
    -0.07
    åıĬæŶåIJij
    -0.06
     insomma
    -0.06
    æĺ¯ä¸İ
    -0.06
    itava
    -0.06
    FromString
    -0.06
    åIJij
    -0.06
    POSITIVE LOGITS
    ä¹ĭéĹ´æľī
    0.08
    éĥ½å¾Ī好
    0.08
    ä¹ĭéĹ´çļĦ
    0.07
    æµ·é»ĺ
    0.07
    alani
    0.07
    ä¹ĭéĸĵ
    0.07
     ìŀ
    0.07
    ãģ©ãģ¡ãĤīãĤĤ
    0.07
    ä¹ĭéĸĵçļĦ
    0.07
    æĹĹé¼ĵ
    0.07
    Activations Density 0.025%

    No Known Activations