© 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. 30971
    Prev
    Next
    INDEX
    Explanations

    software programming languages

    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
    åĽº
    -0.07
    举è¡Ĺ
    -0.07
    ä½ľä¸ºä¸Ģç§į
    -0.06
    ows
    -0.06
    å·¥ä½ľä»»åĬ¡
    -0.06
    SR
    -0.06
    åĽºåĮĸ
    -0.06
     almonds
    -0.06
    redi
    -0.06
    å¤ĸæĮĤ
    -0.06
    POSITIVE LOGITS
    à¤Łà¤ķ
    0.08
    ĵĺ
    0.08
    æľĶ
    0.07
    หมà¸Ń
    0.07
    åĪĿæģĭ
    0.07
    å¾·éŁ³
    0.07
    unut
    0.07
    utando
    0.07
    यर
    0.07
    дÑĥа
    0.07
    Activations Density 0.001%

    No Known Activations