© 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. 27153
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols

    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
    μÏĢ
    -0.07
    à¹Īà¸Ļ
    -0.07
    íĨ
    -0.07
    åľ¨ä»ĬåIJİçļĦ
    -0.06
    åij½è¿IJ
    -0.06
    å¦ĩ
    -0.06
     flourishing
    -0.06
    otka
    -0.06
     fér
    -0.06
    ures
    -0.06
    POSITIVE LOGITS
     Resta
    0.08
    æĺ¥èĬ±
    0.08
    аÑĤÑĥÑĢа
    0.08
    йл
    0.08
    ÑĢаÑĤа
    0.07
    arged
    0.07
    itari
    0.07
    yse
    0.07
    _own
    0.07
    анÑĤа
    0.07
    Activations Density 0.013%

    No Known Activations