© 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. 15816
    Prev
    Next
    INDEX
    Explanations

    scientific outcome or prediction

    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
     irgend
    -0.07
    å¾Īå¤ļåľ°æĸ¹
    -0.07
    åĪļæīį
    -0.07
     crappy
    -0.07
     évent
    -0.07
    åĽ¾çīĩæĪĸ
    -0.07
    æľīä¸ĭåĪĹ
    -0.07
    æĪĸèĢħåħ¶ä»ĸ
    -0.07
    åħĥåĪ°
    -0.07
    åģĩåĨĴ伪åĬ£
    -0.07
    POSITIVE LOGITS
     (...)
    0.08
    åľ¨åħ¶ä¸Ń
    0.08
    \\/
    0.08
    ÑĦÑĤ
    0.07
     uni
    0.07
    ç«ŁçĦ¶æĺ¯
    0.07
     vali
    0.07
     novel
    0.07
    ,...
    0.07
    "--
    0.07
    Activations Density 7.840%

    No Known Activations