© 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. 63661
    Prev
    Next
    INDEX
    Explanations

    numbers as ordinal or cardinal quantities

    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
     few
    -0.08
    वाल
    -0.07
    Interop
    -0.07
    endl
    -0.07
    åĩłä¸ĩ
    -0.07
    ifacts
    -0.07
    ×ŀ×¢
    -0.07
    åıĬæľįåĬ¡
    -0.07
    emput
    -0.07
    åĴĮçłĶ究
    -0.07
    POSITIVE LOGITS
    é·
    0.07
    è¿Ļ个æķ°åŃĹ
    0.07
    å¦ŀ
    0.07
     appunto
    0.06
    çī²
    0.06
    æīįèĥ½ä½¿
    0.06
    onas
    0.06
    çĵ
    0.06
    бал
    0.06
     evenly
    0.06
    Activations Density 0.023%

    No Known Activations