© 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. 17184
    Prev
    Next
    INDEX
    Explanations

    parameter and hidden variables

    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
    rne
    -0.08
    imai
    -0.08
    achu
    -0.07
    olver
    -0.07
     Raffa
    -0.07
    ÏĪη
    -0.07
    Å¡a
    -0.07
    maal
    -0.07
    زاÙħ
    -0.07
     accaduto
    -0.07
    POSITIVE LOGITS
    份
    0.08
    ä¿¡
    0.07
     parameter
    0.07
    ixin
    0.07
    åıĺéĩı
    0.07
    ised
    0.06
     T
    0.06
    åĴĮæݧåĪ¶
    0.06
    ord
    0.06
    ä¸ĬçŃī
    0.06
    Activations Density 0.006%

    No Known Activations