© 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. 47060
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation around 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
     break
    -0.07
     âĨĴ
    -0.06
    é«ĺ大
    -0.06
    rol
    -0.06
     specified
    -0.06
     stretch
    -0.05
    æĿ¾
    -0.05
     breaks
    -0.05
    éĽ
    -0.05
    ä¸į带
    -0.05
    POSITIVE LOGITS
    è¿Ļ个åIJįåŃĹåľ¨åĽ½å¤ĸ
    0.09
    uetype
    0.09
    ,strong
    0.09
    .ali
    0.09
    áĥļáĥĿáĥij
    0.09
    çīĪæĿĥåĿĩ
    0.08
    对人
    0.08
    overall
    0.08
    OperationException
    0.08
    å¾·åŁº
    0.08
    Activations Density 0.019%

    No Known Activations