© 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. 3786
    Prev
    Next
    INDEX
    Explanations

    operator or eigenvalue

    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
    ิà¸Ļ
    -0.09
    NgModule
    -0.07
    ChangeEvent
    -0.07
     depleted
    -0.06
    åħ¨éĿ¢åIJ¯åĬ¨
    -0.06
    æĸ°æľĪ
    -0.06
    æŃī
    -0.06
    é¦Ļæł¼éĩĮæĭī
    -0.06
    åĪĨéĴŁåīį
    -0.06
     ister
    -0.06
    POSITIVE LOGITS
     eigen
    0.10
    Eigen
    0.09
     Eigen
    0.08
    /operator
    0.08
     commuting
    0.08
    åIJĮå·¥
    0.07
    azel
    0.07
    åĬłåħ³æ³¨
    0.07
     Operator
    0.07
    å®ĺæĸ¹å¾®ä¿¡
    0.07
    Activations Density 0.011%

    No Known Activations