© 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. 61536
    Prev
    Next
    INDEX
    Explanations

    stereoisomers, levels, amino acids

    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
    饼
    -0.08
    olum
    -0.07
    razier
    -0.07
     Duk
    -0.07
    dling
    -0.06
    éķ¿ä¹IJ
    -0.06
    éĹ²
    -0.06
    é²²
    -0.06
    odu
    -0.06
    UCK
    -0.06
    POSITIVE LOGITS
    æĺĤ
    0.09
     masing
    0.09
     independently
    0.08
    á»Ĺi
    0.08
    å¦Ĥä½ķéĢīæĭ©
    0.08
    æĺ¯æ¯ı个
    0.08
    each
    0.08
    åIJĦèĩª
    0.08
    á»iji
    0.08
    Choices
    0.08
    Activations Density 0.031%

    No Known Activations