© 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. 29838
    Prev
    Next
    INDEX
    Explanations

    assessment and prediction verbs

    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
    use
    -0.08
    å°½åĬĽ
    -0.07
    ł
    -0.07
    åIJĪ
    -0.07
     use
    -0.07
    تز
    -0.07
    大åįĬ
    -0.06
    åľ¨æŃ¤åŁºç¡Ģä¸Ĭ
    -0.06
    _USE
    -0.06
    为好åıĭ
    -0.06
    POSITIVE LOGITS
    åĴĮæĶ¹åĸĦ
    0.11
    åĴĮæĮĩ导
    0.11
    åĴĮä¿ĿæĬ¤
    0.10
    åĴĮæıIJé«ĺ
    0.10
    åĴĮæıIJåįĩ
    0.10
    åĴĮæĶ¹è¿Ľ
    0.09
     ×ķ׾×Ķ
    0.09
    åĴĮçIJĨ解
    0.09
     purposes
    0.09
    åĴĮ管çIJĨ
    0.08
    Activations Density 0.353%

    No Known Activations