© 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. 14189
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
    bern
    -0.07
    鸾
    -0.07
    è¿Ŀåıįä¸Ĭè¿°
    -0.07
    fo
    -0.06
    Ul
    -0.06
    æ¯ıå¹´éĥ½ä¼ļ
    -0.06
    erna
    -0.06
     tune
    -0.06
    hdl
    -0.06
    绾ç»İ
    -0.06
    POSITIVE LOGITS
     subtotal
    0.08
    ÛĮات
    0.07
    гал
    0.07
    ستÙĨ
    0.07
    æĽ´å¤ļåĽŀçŃĶ
    0.07
    aub
    0.07
    å®Ĺ
    0.07
     gunmen
    0.07
    intern
    0.07
    rac
    0.07
    Activations Density 0.007%

    No Known Activations