© 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. 14148
    Prev
    Next
    INDEX
    Explanations

    data source and functions

    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
    imals
    -0.07
    ly
    -0.06
    niki
    -0.06
     Kand
    -0.06
    kör
    -0.06
    pri
    -0.06
    st
    -0.06
    m
    -0.06
     "-"
    -0.06
    imal
    -0.06
    POSITIVE LOGITS
    atha
    0.07
     ''),
    0.07
    ppelin
    0.07
    åѦä¸İ
    0.07
    ajat
    0.07
    ocused
    0.07
    onsel
    0.07
     warta
    0.07
    .),
    0.07
    ختÙĩ
    0.07
    Activations Density 0.124%

    No Known Activations