© 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. 61897
    Prev
    Next
    INDEX
    Explanations

    programming status indicators

    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
    åħĭæĸ¯
    -0.07
    个åĽŀçŃĶ
    -0.07
    жениÑı
    -0.07
     angekommen
    -0.07
    wich
    -0.07
    ting
    -0.06
    .getClass
    -0.06
    голо
    -0.06
    [class
    -0.06
    羽翼
    -0.06
    POSITIVE LOGITS
    æĪIJåĬŁåIJİ
    0.08
    æĪIJåĬŁçİĩ
    0.08
    edah
    0.07
    Success
    0.07
     success
    0.07
    åħĪæĬĬ
    0.07
    æĪIJåĬŁ
    0.07
     Success
    0.07
     ÙħÙĪÙģÙĤ
    0.07
    OLER
    0.07
    Activations Density 0.058%

    No Known Activations