© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12106
    Prev
    Next
    INDEX
    Explanations

    includes or encompasses

    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
    amba
    -0.07
    ocere
    -0.07
    ä¹ħä¹ĭ
    -0.07
    chie
    -0.07
    µ
    -0.07
    pare
    -0.07
    lias
    -0.07
    uson
    -0.07
    zis
    -0.07
    olas
    -0.07
    POSITIVE LOGITS
    ä¹ŁåĮħæĭ¬
    0.13
    åĮħæĭ¬äºĨ
    0.13
    åĮħåIJ«äºĨ
    0.12
    includes
    0.12
    /include
    0.12
     includes
    0.12
    è¿ĺåĮħæĭ¬
    0.11
    åĮħæĭ¬
    0.11
    åĮħåIJ«
    0.11
     Includes
    0.11
    Activations Density 0.247%

    No Known Activations