© 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. 23448
    Prev
    Next
    INDEX
    Explanations

    code and math notations

    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
    .vaadin
    -0.07
    zków
    -0.07
    itespace
    -0.07
    fine
    -0.06
     Bust
    -0.06
    kena
    -0.06
     MAIS
    -0.06
    å¾ģæĸĩ
    -0.06
    ència
    -0.06
    addle
    -0.06
    POSITIVE LOGITS
    ignon
    0.08
    bern
    0.07
    -ves
    0.07
    uç
    0.07
    ç»İ
    0.07
    sink
    0.07
    ä¸»å¼ł
    0.07
    Sing
    0.07
    anson
    0.07
    εÏģι
    0.07
    Activations Density 0.010%

    No Known Activations