© 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. 20003
    Prev
    Next
    INDEX
    Explanations

    political titles and programming elements

    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
    åĽ½åĨħçļĦ
    -0.07
    ä¸ĭ载次æķ°
    -0.07
     Wade
    -0.07
    èIJ¤
    -0.07
    ifes
    -0.06
     extr
    -0.06
     nub
    -0.06
    à¸Ĺะ
    -0.06
    åħļæĹĹ
    -0.06
    åľ¨åĽ½åĨħ
    -0.06
    POSITIVE LOGITS
    æŁIJä¸Ģ个
    0.14
    æŁIJä¸Ģ
    0.14
    åľ¨æŁIJ
    0.14
    æŁIJ
    0.13
    æŁIJ个
    0.12
    æŁIJåĢĭ
    0.11
    æŁIJä¸Ģ天
    0.11
    ä¹ĭä¸ĢçļĦ
    0.10
    çī¹å®ļ
    0.10
    ä¹ĭä¸Ģ
    0.09
    Activations Density 0.380%

    No Known Activations