© 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. 48251
    Prev
    Next
    INDEX
    Explanations

    international society or organisation

    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
    	TokenName
    -0.08
    <|box_end|>
    -0.08
    usted
    -0.08
     ritu
    -0.07
    oyer
    -0.07
    otate
    -0.07
    æ»¡çľ¼
    -0.07
    ustin
    -0.07
    upas
    -0.07
    -done
    -0.07
    POSITIVE LOGITS
    ç§ijåѦ
    0.06
    craft
    0.06
    nest
    0.06
    osci
    0.06
    ä¸Ńå¿ĥå·¥ä½ľ
    0.06
    e
    0.06
    orough
    0.06
    çİĦå¾·
    0.06
    ²
    0.05
    éļ¾
    0.05
    Activations Density 0.315%

    No Known Activations