© 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. 12259
    Prev
    Next
    INDEX
    Explanations

    ? followed by you

    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
    arez
    -0.07
    lingen
    -0.07
    é¡»æıIJä¾Ľ
    -0.07
    ður
    -0.07
    .gnu
    -0.07
    ĴĪ
    -0.07
    ernes
    -0.07
    implicit
    -0.07
     uncon
    -0.07
    verket
    -0.07
    POSITIVE LOGITS
    æĮºå¥½
    0.07
     nicer
    0.07
     handy
    0.07
     easier
    0.07
     preferable
    0.07
    课åīį
    0.07
    æĽ´å¥½
    0.07
    å¼Ģå¼Ģå¿ĥ
    0.07
    没æľīå¿ħè¦ģ
    0.07
     initialize
    0.06
    Activations Density 0.011%

    No Known Activations