© 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. 64693
    Prev
    Next
    INDEX
    Explanations

    ages or ranges

    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
    lain
    -0.08
    座
    -0.08
    esses
    -0.08
     Sitz
    -0.08
    åĿŀ
    -0.08
    atis
    -0.07
     uncomp
    -0.07
    licable
    -0.07
    omp
    -0.07
    ай
    -0.07
    POSITIVE LOGITS
    ordo
    0.07
    æĪĬ
    0.06
    ige
    0.06
    رج
    0.06
    alas
    0.06
    atat
    0.06
    _DT
    0.06
    PTS
    0.06
    åѦåĮº
    0.06
    ADAS
    0.06
    Activations Density 0.002%

    No Known Activations