© 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. 63010
    Prev
    Next
    INDEX
    Explanations

    emphasis, value, or stresses

    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
     intending
    -0.08
    วยา
    -0.07
    sel
    -0.07
    ayat
    -0.07
    pedia
    -0.07
    egi
    -0.07
    çļĦæīĢæľī
    -0.07
    ield
    -0.07
    ecome
    -0.06
    thro
    -0.06
    POSITIVE LOGITS
    çļĦå°±æĺ¯
    0.10
    äºĨ对
    0.09
    çļĦéĥ½æĺ¯
    0.09
    çļĦæĺ¯
    0.08
    ä»Ģä¹Īåij¢
    0.08
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    0.08
    çļĦè¿ĺæĺ¯
    0.07
    entially
    0.07
    å®ŀæķĪ
    0.07
    æ²ŁéĢļåĴĮ
    0.07
    Activations Density 0.089%

    No Known Activations