© 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. 39632
    Prev
    Next
    INDEX
    Explanations

    support

    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
    åħ´å¥ĭåľ°
    -0.07
    åIJĮåIJį
    -0.06
    æľĿ天
    -0.06
    å¿ħ究
    -0.06
    并ç»ĵåIJĪ
    -0.06
     disciplined
    -0.06
    Äįnosti
    -0.06
     inherits
    -0.06
    å°ıéķ¿åģĩ
    -0.05
    ç»ĻæĪij们带æĿ¥
    -0.05
    POSITIVE LOGITS
    /support
    0.16
    åĴĮæĶ¯æĮģ
    0.15
    /help
    0.15
     support
    0.14
     assistance
    0.14
    æĶ¯æĮģ
    0.13
    çļĦæĶ¯æĮģ
    0.13
    support
    0.13
     Support
    0.13
     supportive
    0.13
    Activations Density 0.240%

    No Known Activations