© 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. 55372
    Prev
    Next
    INDEX
    Explanations

    priority and prioritization

    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
     lót
    -0.09
    éģĹçĹĩ
    -0.09
    ruh
    -0.08
    дÑĭй
    -0.08
    ยัà¸Ļ
    -0.08
    æ¯ĶæĭŁ
    -0.08
    ulte
    -0.08
    halb
    -0.08
    dene
    -0.08
    opyright
    -0.08
    POSITIVE LOGITS
    ä¸Ĭçģ«
    0.08
    ential
    0.08
    æĢ§çļĦ
    0.07
    äºĭ项
    0.07
    innacle
    0.07
    ä¸ĩåĪĨ
    0.07
    æĢ§åľ°
    0.06
    ìĤ¬íķŃ
    0.06
    ä¸ĬåİķæīĢ
    0.06
    chn
    0.06
    Activations Density 0.014%

    No Known Activations