© 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. 22495
    Prev
    Next
    INDEX
    Explanations

    code diffs and programming constructs

    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
    à´¤àµį
    -0.07
    imir
    -0.07
    ç¾Ĭç¾Ĭ
    -0.07
    ä¸Ĭå¹´
    -0.07
    chts
    -0.07
    ä¾µçĬ¯äºĨæĤ¨çļĦ
    -0.07
    uschen
    -0.06
     Kind
    -0.06
    md
    -0.06
    opts
    -0.06
    POSITIVE LOGITS
    leston
    0.08
    ä¹ĭä¸į
    0.07
    å·§
    0.07
    uais
    0.07
    abs
    0.07
    asser
    0.07
    ras
    0.06
    labs
    0.06
    stadt
    0.06
    å°ıæĹ¶å·¦åı³
    0.06
    Activations Density 0.003%

    No Known Activations