© 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. 39405
    Prev
    Next
    INDEX
    Explanations

    in practice

    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
     rightful
    -0.08
    æľ¬èº«å°±æĺ¯
    -0.08
    æľ¬èº«çļĦ
    -0.08
    çIJĨ论ä¸Ĭ
    -0.08
    çIJĨæīĢ
    -0.08
    _None
    -0.07
     respective
    -0.07
    ä¼ĺèī¯ä¼łç»Ł
    -0.07
    ä¹ĭ乡
    -0.07
    ä¹ĭåIJİçļĦ
    -0.07
    POSITIVE LOGITS
     implementations
    0.10
    å®ŀè·µä¸Ń
    0.10
    implementation
    0.09
    Implementation
    0.09
     implementation
    0.09
    å¾Ģå¾Ģ
    0.09
    常常
    0.09
     Implementation
    0.08
     sering
    0.08
     often
    0.08
    Activations Density 0.016%

    No Known Activations