© 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. 22469
    Prev
    Next
    INDEX
    Explanations

    structural delimiters with numbers/variables

    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
    bonne
    -0.07
    omin
    -0.06
    è´¨çĸij
    -0.06
    æ´ŀéĩĮ
    -0.06
    reck
    -0.06
    ä¸Ģä¸ªäººåľ¨
    -0.06
    åĭ¤åĭī
    -0.06
    çī©çļĦ
    -0.06
    %S
    -0.06
    åĪĨéħį
    -0.06
    POSITIVE LOGITS
    aign
    0.09
    apé
    0.08
    Å«k
    0.08
    ésil
    0.07
    amment
    0.07
    miny
    0.07
    驻马
    0.07
    anker
    0.07
    -------------</
    0.07
    =\"#
    0.07
    Activations Density 0.006%

    No Known Activations