© 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. 13795
    Prev
    Next
    INDEX
    Explanations

    function and script context

    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
    utes
    -0.07
    ten
    -0.06
    å¼Ĥ
    -0.06
    .STATE
    -0.06
    说ä¸į
    -0.06
    è¿ĩ渡
    -0.06
    emy
    -0.06
    ÑĪÑĭ
    -0.06
    ä¸įæĥĬ
    -0.06
    ilon
    -0.06
    POSITIVE LOGITS
    çĮ®èº«
    0.08
     expecting
    0.08
    ipot
    0.08
    æİ¥è¯Ĭ
    0.07
    -package
    0.07
    ä¼łäºº
    0.07
    ستاÙĨ
    0.07
    ÃŃna
    0.07
     malad
    0.07
    obel
    0.07
    Activations Density 0.001%

    No Known Activations