© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10690
    Prev
    Next
    INDEX
    Explanations

    ending punctuation

    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
    éĿłåīį
    -0.07
    à¸ĵะ
    -0.07
    _REASON
    -0.07
    اعد
    -0.07
     anzi
    -0.07
    Helvetica
    -0.07
    istaa
    -0.07
    atsby
    -0.07
    èves
    -0.07
    éªı
    -0.07
    POSITIVE LOGITS
    GRE
    0.07
    äºĶèĬ±
    0.06
    ç«ĻåĨħæIJľç´¢
    0.06
    ÑĥÑĢе
    0.06
     sight
    0.06
    åħĭæľįåĽ°éļ¾
    0.06
     moc
    0.06
     summed
    0.06
    romo
    0.06
    lite
    0.06
    Activations Density 0.523%

    No Known Activations