© 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. 48012
    Prev
    Next
    INDEX
    Explanations

    numbers and list separators

    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
    ebra
    -0.07
    olt
    -0.07
     yourselves
    -0.07
    ä¸įåĴĮ
    -0.06
    ัà¸ļ
    -0.06
    UNUSED
    -0.06
    .ua
    -0.06
    ([{
    -0.06
    .Must
    -0.06
    lica
    -0.06
    POSITIVE LOGITS
    çıĪ
    0.07
    maal
    0.07
    гоÑĢе
    0.07
     McGr
    0.07
    rapper
    0.07
     Ø°ÙĬ
    0.07
     prime
    0.07
    athers
    0.07
    utas
    0.07
    atorie
    0.07
    Activations Density 0.009%

    No Known Activations