© 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. 1325
    Prev
    Next
    INDEX
    Explanations

    Visual Studio, LaTeX

    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
    atta
    -0.07
    æľ¬å½ĵ
    -0.06
    iders
    -0.06
    æķıæĦŁçļĦ
    -0.06
    hte
    -0.06
    ace
    -0.06
    稿
    -0.06
    åıªæĺ¯ä¸ºäºĨ
    -0.06
    ettes
    -0.06
    cloak
    -0.06
    POSITIVE LOGITS
    AndGet
    0.07
     fé
    0.07
    wel
    0.07
    Against
    0.07
    è¿Ļæīįæĺ¯
    0.07
    è¿Ļå°±æĺ¯
    0.07
    æīįæĺ¯
    0.06
    ulty
    0.06
    _='
    0.06
     аÑĥ
    0.06
    Activations Density 0.048%

    No Known Activations