© 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. 22089
    Prev
    Next
    INDEX
    Explanations

    `import`, `run`, `meta`, `charset`, `if`, `text`, `link`

    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
     ////
    -0.08
    kena
    -0.08
    .getSimpleName
    -0.08
    odle
    -0.07
    amanan
    -0.07
    gaard
    -0.07
    omm
    -0.07
    åį´è¦ģ
    -0.07
    .utf
    -0.07
    ingles
    -0.07
    POSITIVE LOGITS
    lje
    0.07
    èĢĮåľ¨
    0.07
    aid
    0.06
    çĨ
    0.06
    rist
    0.06
    ä¾µçĬ¯äºĨæĤ¨çļĦæĿĥçĽĬ
    0.06
    ’.
    0.06
    inv
    0.06
    erk
    0.06
    wer
    0.06
    Activations Density 0.138%

    No Known Activations