© 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. 51787
    Prev
    Next
    INDEX
    Explanations

    discrete and quantized measurements

    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
    åĢ¾æĥħ
    -0.09
     homog
    -0.08
    ERM
    -0.08
     Wetter
    -0.08
    inois
    -0.07
    áĥĶáĥĹ
    -0.07
     diversion
    -0.07
    ãĥ¼ãĥģ
    -0.07
    åij¨ä¸Ģèĩ³
    -0.07
    .Merge
    -0.07
    POSITIVE LOGITS
     discrete
    0.08
    æĿŁç¼ļ
    0.08
    éĴī
    0.08
     discret
    0.08
    åıªèĥ½åľ¨
    0.07
     imposed
    0.07
     enforced
    0.07
    æĺ¯æľīéĻIJçļĦ
    0.07
    縼
    0.07
     jag
    0.07
    Activations Density 0.005%

    No Known Activations