© 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. 60953
    Prev
    Next
    INDEX
    Explanations

    music video

    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
    èĭĩ
    -0.07
    åĮĨ
    -0.07
    urance
    -0.07
     پار
    -0.06
    æĪij们éĥ½æĺ¯
    -0.06
    orter
    -0.06
    åĬ¨æľº
    -0.06
    ãĥĹ
    -0.06
    åı¯ä»¥æł¹æį®èĩªå·±çļĦ
    -0.06
    à¸Ķà¹īวยà¸ģัà¸Ļ
    -0.06
    POSITIVE LOGITS
     associated
    0.10
    associated
    0.09
    ingerprint
    0.08
     associé
    0.08
    éļıä¹ĭ
    0.08
    æĺ¯åħ¶
    0.08
     associés
    0.07
     asoci
    0.07
    åħ¨æĸĩéĺħ读
    0.07
    ån
    0.07
    Activations Density 0.107%

    No Known Activations