© 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. 62231
    Prev
    Next
    INDEX
    Explanations

    frequency and rarity contrast

    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
    ä»Ģä¹Īéĥ½æ²¡æľī
    -0.07
    æĦŁåIJĮ
    -0.07
    iola
    -0.07
    ä¸įå¾Ĺ以任ä½ķ
    -0.07
    å°±æĹłæ³ķ
    -0.07
    åĿĩåºĶ
    -0.07
    å¿ħé¡»åħĪ
    -0.07
    :first
    -0.07
     implanted
    -0.07
    EGI
    -0.07
    POSITIVE LOGITS
     rarely
    0.10
    ä¸į太
    0.10
    ä¹Łä¸į太
    0.10
     rare
    0.10
     ÑĢедко
    0.10
     Rare
    0.10
    ç½ķ
    0.09
     raczej
    0.09
    schlag
    0.09
     uncommon
    0.09
    Activations Density 0.077%

    No Known Activations