© 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. 10318
    Prev
    Next
    INDEX
    Explanations

    expressing favor, victory, or allowance

    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
    адÑĮ
    -0.08
     recens
    -0.07
    ueb
    -0.07
    IZZ
    -0.07
    اض
    -0.07
    odel
    -0.07
    ëĿ¼ìĿ¸
    -0.07
    elsey
    -0.07
    occhi
    -0.07
    AGON
    -0.07
    POSITIVE LOGITS
     favor
    0.09
     favored
    0.09
     faveur
    0.07
     favour
    0.07
     favoured
    0.07
     favorecer
    0.07
     تÙĤدÙħ
    0.07
    æľīåĪ©äºİ
    0.07
     whichever
    0.07
    fav
    0.07
    Activations Density 0.431%

    No Known Activations