© 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. 34270
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and sequences

    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
    åĴ«å°º
    -0.07
    ä¸īå²ģ
    -0.07
    iese
    -0.07
    uur
    -0.07
    types
    -0.07
    TypeInfo
    -0.07
    æĤį
    -0.06
    ä¼Ł
    -0.06
    .getOwnProperty
    -0.06
    gether
    -0.06
    POSITIVE LOGITS
    ordinal
    0.13
    åºıåı·
    0.12
    ç¼ĸåı·
    0.12
     ordinal
    0.11
     numbering
    0.11
     numbered
    0.11
    Ordinal
    0.11
    .ordinal
    0.11
     number
    0.11
     номеÑĢ
    0.11
    Activations Density 0.169%

    No Known Activations