© 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. 13096
    Prev
    Next
    INDEX
    Explanations

    French and non-English words

    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
    以ä¸ĬåĨħ容
    -0.07
    ower
    -0.06
     dele
    -0.06
    ëĭ¥
    -0.06
     infine
    -0.06
    abh
    -0.06
     mon
    -0.06
    teres
    -0.06
    dern
    -0.06
    inn
    -0.06
    POSITIVE LOGITS
    åIJĮä¸Ĭ
    0.09
    ä½ķçŃī
    0.08
    æİ¥çĿĢ
    0.08
    ERM
    0.07
    åIJĮçIJĨ
    0.07
    endah
    0.07
    woo
    0.07
    voy
    0.07
    anking
    0.07
    .Strict
    0.07
    Activations Density 0.194%

    No Known Activations