© 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. 41605
    Prev
    Next
    INDEX
    Explanations

    continue reading

    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
    opr
    -0.08
    ċ
    -0.07
    ³³³³³³³³
    -0.07
    enaar
    -0.07
    ³³³³
    -0.07
    ktor
    -0.07
    ORO
    -0.07
    inally
    -0.07
    ewis
    -0.07
    _PT
    -0.06
    POSITIVE LOGITS
    adel
    0.08
    æĬĬåŃ©åŃIJ
    0.07
    eid
    0.07
    æ¯ı项
    0.07
    帶
    0.07
    ç§
    0.06
    udir
    0.06
    çļĦæŀĹ
    0.06
    æŃ¹
    0.06
    带åĪ°
    0.06
    Activations Density 0.002%

    No Known Activations