© 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. 28291
    Prev
    Next
    INDEX
    Explanations

    for example

    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
    enje
    -0.07
    ells
    -0.06
    elts
    -0.06
    ä¹Ŀéĩį
    -0.06
    æIJĶ
    -0.06
    hear
    -0.06
    jj
    -0.06
    asa
    -0.06
    æĺĵ
    -0.06
    èµĸ
    -0.06
    POSITIVE LOGITS
    à¸Ķัà¸ĩ
    0.07
    ÃŃb
    0.07
    aurant
    0.07
    aning
    0.07
    ĮĢ
    0.07
    Õ¹
    0.07
     beispielsweise
    0.07
     bijvoorbeeld
    0.07
    çļĦè¿Ļç§į
    0.07
    odal
    0.07
    Activations Density 0.004%

    No Known Activations