© 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. 32812
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by clause

    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
    ingos
    -0.08
    hlas
    -0.08
    æĪijçļĦ书æŀ¶
    -0.08
    æĸ°åŀĭçļĦ
    -0.07
    ç®Ģ书
    -0.07
    æĽ¾ç»ıæĺ¯
    -0.07
    ifestyles
    -0.07
    resa
    -0.07
    åıĭæĥħéĵ¾æİ¥
    -0.07
    æ¯Ķä¸įä¸Ĭ
    -0.07
    POSITIVE LOGITS
    å¾Ģå¾Ģ
    0.10
    å°½éĩı
    0.09
     often
    0.08
    å¾Ģå¾Ģæĺ¯
    0.08
     style
    0.07
    æ¯ıä¸Ģ
    0.07
    onge
    0.07
    ongen
    0.07
    often
    0.07
     throughout
    0.07
    Activations Density 0.110%

    No Known Activations