© 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. 17383
    Prev
    Next
    INDEX
    Explanations

    religious figures, technical terms, and cooking methods

    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
    plevel
    -0.07
    odore
    -0.07
    ksam
    -0.07
    cht
    -0.07
    åIJĥåIJĥ
    -0.07
    æ²ĥæĸ¯
    -0.07
    ogo
    -0.07
    æĥŁä¸Ģ
    -0.07
    stype
    -0.07
    okon
    -0.07
    POSITIVE LOGITS
    å®ļä¹ī为
    0.09
    è¿Ļ个è¯į
    0.08
    æľ¬èº«å°±æĺ¯
    0.08
    åIJįåī¯åħ¶å®ŀ
    0.08
     Defined
    0.07
     appunto
    0.07
    æĮĩ
    0.07
    ãģ¨åij¼ãģ°ãĤĮãĤĭ
    0.07
    å°±æĺ¯æĮĩ
    0.07
    æŃ»
    0.07
    Activations Density 0.273%

    No Known Activations