© 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. 48979
    Prev
    Next
    INDEX
    Explanations

    text preview or excerpt

    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
    ertest
    -0.09
    otland
    -0.07
    igung
    -0.07
    verg
    -0.07
    ingo
    -0.07
    áºŃu
    -0.07
     autobio
    -0.07
    anism
    -0.07
    imenta
    -0.07
    ؤÙĦ
    -0.07
    POSITIVE LOGITS
    åħ¨æĸĩ
    0.09
    éĥ¨åĪĨåĨħ容
    0.07
     ePub
    0.07
    åħ¨éĥ¨åĨħ容
    0.07
     pdf
    0.07
     plain
    0.07
    pdf
    0.06
    inki
    0.06
    åħ¨éĥ¨çļĦ
    0.06
    apters
    0.06
    Activations Density 0.037%

    No Known Activations