© 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. 33223
    Prev
    Next
    INDEX
    Explanations

    source of

    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
    undance
    -0.08
    ä»ħæıIJä¾Ľä¿¡æģ¯
    -0.08
    ampp
    -0.08
    è¿ŀåIJĮ
    -0.07
     setSelected
    -0.07
    ooth
    -0.07
    麹
    -0.07
    amn
    -0.07
    ilha
    -0.07
    èģĮä½įè¦ģæ±Ĥ
    -0.07
    POSITIVE LOGITS
     sources
    0.20
    æĿ¥æºIJ
    0.20
     Sources
    0.17
    çļĦæĿ¥æºIJ
    0.16
     source
    0.16
    ä¾ĨæºIJ
    0.16
    sources
    0.15
     fuentes
    0.15
    Sources
    0.14
    /sources
    0.14
    Activations Density 0.166%

    No Known Activations