© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50313
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    enville
    -0.07
    è¾Ļ
    -0.07
    æľĢæľĢ
    -0.07
    atera
    -0.07
    åIJĮ声
    -0.07
    ä¸ĢåIJĮ
    -0.07
     поко
    -0.07
    born
    -0.07
    éĤ£éģĵ
    -0.07
    ä¸İåħ±
    -0.07
    POSITIVE LOGITS
     simpl
    0.08
     simplified
    0.08
    ç®ĢåĮĸ
    0.08
    imis
    0.07
    urd
    0.07
    è¤
    0.07
    има
    0.07
    ara
    0.07
    rees
    0.06
    ç®Ģ便
    0.06
    Activations Density 0.014%

    No Known Activations