© 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. 9643
    Prev
    Next
    INDEX
    Explanations

    charts, lists, or descriptions

    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
     ÑĦле
    -0.08
    ủa
    -0.08
    anos
    -0.08
    è´¹çļĦ
    -0.08
    vented
    -0.08
    ebi
    -0.08
    就容æĺĵ
    -0.08
    à¸ļาà¸ģ
    -0.08
    ThreadPool
    -0.08
    _defaults
    -0.08
    POSITIVE LOGITS
     final
    0.07
    çļĦåIJĮæŶ
    0.07
    at
    0.07
    alts
    0.07
    دÙĩ
    0.07
    以åıĬ缸åħ³
    0.07
    以åıĬ
    0.06
     part
    0.06
    åIJĮæĹ¶ä¹Ł
    0.06
     while
    0.06
    Activations Density 0.012%

    No Known Activations