© 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. 12071
    Prev
    Next
    INDEX
    Explanations

    Lyapunov Exponents, leaves, saddle

    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
    楼å®ĩ
    -0.07
    -0.07
     spare
    -0.06
    èĢĮ论
    -0.06
    å½ĵ头
    -0.06
    ä¸Ģè¡Į
    -0.06
    å¾ĹæĦı
    -0.06
    æ²½
    -0.06
     tall
    -0.06
    ROT
    -0.06
    POSITIVE LOGITS
    emma
    0.08
    éĢļå¾Ģ
    0.08
    nown
    0.08
    .Exit
    0.08
    è²
    0.08
    _ESCAPE
    0.08
    siÄĻ
    0.08
     ÑĤоп
    0.08
    isser
    0.07
    annie
    0.07
    Activations Density 0.005%

    No Known Activations