© 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. 10344
    Prev
    Next
    INDEX
    Explanations

    many, plenty, ton, number, countless, numerous

    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
    ại
    -0.08
    ãģªãģĦãģ¨
    -0.08
     fu
    -0.08
    åģıé«ĺ
    -0.07
    é¢Ŀå¤ĸ
    -0.07
    oplevel
    -0.07
    Extra
    -0.07
    sey
    -0.07
    ãģ£ãģįãĤĬ
    -0.07
    althy
    -0.07
    POSITIVE LOGITS
     countless
    0.12
    มาà¸ģมาย
    0.12
    å¤ļç§įå¤ļæł·
    0.11
    太å¤ļäºĨ
    0.11
     many
    0.11
    ä¼Ĺå¤ļ
    0.11
    æľīå¾Īå¤ļç§į
    0.11
    æľī许å¤ļ
    0.11
    ä¸įèĥľæķ°
    0.11
     numerous
    0.10
    Activations Density 0.629%

    No Known Activations