© 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. 25392
    Prev
    Next
    INDEX
    Explanations

    .ly or al

    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
    çŁ³æ¡¥
    -0.08
    orda
    -0.08
    oyo
    -0.07
    haft
    -0.07
    éĥ¨åĪĨ
    -0.07
    è¨
    -0.07
    PageIndex
    -0.07
    izm
    -0.07
    opause
    -0.07
    intendent
    -0.07
    POSITIVE LOGITS
    å¹¶è¿Ľ
    0.07
    unj
    0.07
    abee
    0.07
    ç©¿ä¸ĬäºĨ
    0.06
    elser
    0.06
    ä¸įå¾Ĺæĵħèĩª
    0.06
     Fowler
    0.06
    ä¸įå¾Ĺ以任ä½ķ
    0.06
    _BGR
    0.06
    utat
    0.06
    Activations Density 0.003%

    No Known Activations