© 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. 51133
    Prev
    Next
    INDEX
    Explanations

    SELECT statement

    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
     ded
    -0.06
     Frei
    -0.06
    íħ
    -0.06
     dedicated
    -0.06
    解
    -0.06
     may
    -0.06
     unsus
    -0.06
    æ¸ħçIJĨ
    -0.06
     sol
    -0.06
    åĽłä¸ºè¿Ļ
    -0.06
    POSITIVE LOGITS
    æİĥ
    0.09
    èī²åĪĹ
    0.08
    æ³ķæĺ¯
    0.07
    QC
    0.07
    :start
    0.07
    åĨħ容æĺ¯
    0.07
     lá»ĩ
    0.07
    ารà¸ĸ
    0.07
    /cop
    0.07
    ç½ijåıĭçļĦ
    0.07
    Activations Density 0.003%

    No Known Activations