© 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. 25530
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by common 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
    osite
    -0.09
    umon
    -0.08
     pese
    -0.08
    kod
    -0.08
    ãĤ¸
    -0.07
    дика
    -0.07
    xis
    -0.07
    .statistics
    -0.07
    FFE
    -0.07
    onga
    -0.07
    POSITIVE LOGITS
    ä¾ĭå¦Ĥ
    0.08
    æ¯Ķå¦Ĥ说
    0.08
     many
    0.07
    æľīäºĽ
    0.07
     depending
    0.07
    æ¯Ķå¦Ĥ
    0.07
    æľīåı¯èĥ½æĺ¯
    0.07
    åıĸåĨ³äºİ
    0.07
    举ä¾ĭ
    0.07
    ä½Ĩèĩ³å°ij
    0.07
    Activations Density 0.045%

    No Known Activations