© 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. 10245
    Prev
    Next
    INDEX
    Explanations

    alaska airline crew

    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
    天äºĨ
    -0.07
    ä¸įæĥ§
    -0.07
    åĴĮåĪ©çĶ¨
    -0.06
    èĭį天
    -0.06
    èļģ
    -0.06
    ovski
    -0.06
    并ç»ı
    -0.06
    dep
    -0.06
    à¹Ģà¸Ķิม
    -0.06
    ä¸įè¾ŀ
    -0.06
    POSITIVE LOGITS
    .this
    0.07
    zos
    0.07
    aine
    0.07
    >this
    0.07
    clip
    0.07
    ories
    0.07
     **.**
    0.07
    ...).
    0.06
    inak
    0.06
    ä¸ĢåĬł
    0.06
    Activations Density 0.005%

    No Known Activations