© 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. 56712
    Prev
    Next
    INDEX
    Explanations

    comparative formulations

    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
    åıĮåIJij
    -0.08
    iente
    -0.07
    ichen
    -0.07
    éĢī人
    -0.07
    人æĦı
    -0.07
    sel
    -0.07
    zaak
    -0.07
    精彩åĨħ容
    -0.06
    ä¸Ĭè¿°äºĭå®ŀ
    -0.06
    .nlm
    -0.06
    POSITIVE LOGITS
     comparative
    0.09
     compar
    0.08
    ä¸īåĢį
    0.08
     Comparative
    0.07
    auber
    0.07
    Compar
    0.07
    Original
    0.07
    设
    0.07
    寨
    0.07
    /original
    0.07
    Activations Density 0.001%

    No Known Activations