© 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. 58536
    Prev
    Next
    INDEX
    Explanations

    decreases with age or time

    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
    janya
    -0.07
    å·¥ä½ľä¸Ĭ
    -0.07
    çļĦåĴĮ
    -0.07
    æķĻå¸Ī们
    -0.07
    ÏĥίεÏĤ
    -0.07
    çIJĨ论ä¸İ
    -0.06
    äºĽ
    -0.06
    åĨħéĥ¨çļĦ
    -0.06
    ardan
    -0.06
    ான
    -0.06
    POSITIVE LOGITS
    æŶéĹ´æĺ¯
    0.08
    etime
    0.08
     time
    0.08
    ë¡ľëıĦ
    0.08
     altitude
    0.08
    loff
    0.07
    æŶéĹ´åľ¨
    0.07
     annum
    0.07
    ãĥ«ãĤ¹
    0.07
    gun
    0.07
    Activations Density 0.048%

    No Known Activations