© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 45938
    Prev
    Next
    INDEX
    Explanations

    questions or nouns

    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
    :num
    -0.07
    ',[
    -0.07
    dings
    -0.07
    .optim
    -0.07
    ',['
    -0.07
    à¸Ńุà¸Ķ
    -0.07
    aup
    -0.06
    insa
    -0.06
    inati
    -0.06
    aim
    -0.06
    POSITIVE LOGITS
     Äįin
    0.07
    ulet
    0.07
    ubr
    0.06
     likewise
    0.06
    åĩ¯
    0.06
     kats
    0.06
     Wilkinson
    0.06
    oose
    0.06
    æİĮä¸Ĭ
    0.06
    iá»ģn
    0.06
    Activations Density 0.194%

    No Known Activations