© 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. 1394
    Prev
    Next
    INDEX
    Explanations

    convention, order, dimension, timeframe, semantics, structure

    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
    å°ijéĥ¨åĪĨ
    -0.08
    .MAX
    -0.07
    _WRONG
    -0.07
    åĺĺ
    -0.07
    å¢Ł
    -0.07
    ä¸īæĪIJ
    -0.07
    æĪĸå°ij
    -0.06
    ä½ĨåIJĮæŶ
    -0.06
    ä¸į解
    -0.06
    ä½Ĩä¸įèĥ½
    -0.06
    POSITIVE LOGITS
    -wise
    0.09
    /location
    0.09
     matters
    0.08
    /format
    0.08
     wise
    0.08
    å¾Ĺå½ĵ
    0.08
    å¾Īéĩįè¦ģ
    0.08
    åĴĮåĨħ容
    0.08
     issues
    0.07
     considerations
    0.07
    Activations Density 0.048%

    No Known Activations