© 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. 51612
    Prev
    Next
    INDEX
    Explanations

    closing punctuation

    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
    æµ®
    -0.07
    intl
    -0.07
    åį³
    -0.07
    icens
    -0.07
    undu
    -0.07
    ĥ
    -0.07
    holm
    -0.07
    isht
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    iset
    -0.07
    POSITIVE LOGITS
    带大家
    0.07
    åºĶå½ĵä¾Ŀçħ§
    0.07
    å°ıä¼ĻåŃIJ
    0.07
    ÏĦÏģÏĮ
    0.07
    æĭįä¸ĭ
    0.07
    åıĬåĪ©æģ¯
    0.07
    åįİåºŃ
    0.07
    åħ¬çĽĬäºĭä¸ļ
    0.07
    inning
    0.07
    ogg
    0.07
    Activations Density 0.027%

    No Known Activations