© 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. 25981
    Prev
    Next
    INDEX
    Explanations

    percentage or quantity

    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
    以ä¸ĭ为
    -0.07
    ë£Įê°Ģ
    -0.07
    å¿ĥä¸Ńæľīæķ°
    -0.07
     setattr
    -0.07
    iene
    -0.06
    æī§
    -0.06
    idane
    -0.06
    æĹłä¸Ĭ
    -0.06
    çĦļ
    -0.06
     StartCoroutine
    -0.06
    POSITIVE LOGITS
    utz
    0.07
     spell
    0.07
    è¿Ľè¡Įçİ°åľº
    0.07
    (review
    0.07
     cuest
    0.07
    å¿ĺè®°äºĨ
    0.06
    маÑĤи
    0.06
    Utility
    0.06
    æľ¬å¸Ĥ
    0.06
    çļĦå¦Īå¦Ī
    0.06
    Activations Density 0.029%

    No Known Activations