© 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. 29692
    Prev
    Next
    INDEX
    Explanations

    small, smallest, simplest cases or versions

    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
     åt
    -0.09
    usen
    -0.08
    ä¸įæį¢
    -0.08
    usus
    -0.08
    pled
    -0.08
     неÑı
    -0.08
    _safe
    -0.08
    å¼ı设计
    -0.08
    Streaming
    -0.08
    æĹ¥ä»¥
    -0.08
    POSITIVE LOGITS
    /small
    0.07
    æŀļ举
    0.07
    å°ıçļĦ
    0.07
    /simple
    0.07
    енÑĮ
    0.07
     enumeration
    0.06
     manually
    0.06
    ritt
    0.06
    enum
    0.06
    å®ŀéªĮ
    0.06
    Activations Density 0.018%

    No Known Activations