© 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. 39153
    Prev
    Next
    INDEX
    Explanations

    code syntax: punctuation followed by words

    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
    ="__
    -0.08
    ='../
    -0.08
     '__
    -0.07
    irsch
    -0.07
     ïĤ
    -0.07
    ="_
    -0.07
    YPE
    -0.07
    "https
    -0.07
      ↵↵↵
    -0.06
    >Last
    -0.06
    POSITIVE LOGITS
    ï¸ı
    0.08
    dene
    0.08
    .toUpperCase
    0.07
    <span
    0.07
    áºŃp
    0.07
    .configure
    0.07
    zil
    0.07
     Available
    0.06
    åŁºç¡ĢçŁ¥è¯Ĩ
    0.06
    æĽ´å¤ļ精彩
    0.06
    Activations Density 0.165%

    No Known Activations