© 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. 10963
    Prev
    Next
    INDEX
    Explanations

    WARN and above, newer, certain

    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
    ych
    -0.08
    uttle
    -0.07
    gis
    -0.07
    çīĪæĿĥä¸İåħį责声æĺİ
    -0.07
    NullOrEmpty
    -0.07
    ç¾İ好çļĦåĽŀå¿Ĩ
    -0.07
    addon
    -0.07
    æĪij羣
    -0.07
    ieux
    -0.07
    裳
    -0.07
    POSITIVE LOGITS
     onwards
    0.18
     onward
    0.17
    以åIJİçļĦ
    0.15
    以éĻį
    0.15
    åıĬ以ä¸Ĭ
    0.14
    åıĬ以ä¸ĭ
    0.13
    åıĬ以ä¸ĬçļĦ
    0.13
    ä¹ĭåIJİçļĦ
    0.12
    以å¾Į
    0.11
    èĩªæѤ
    0.11
    Activations Density 0.123%

    No Known Activations