© 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. 22153
    Prev
    Next
    INDEX
    Explanations

    digits of numbers

    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
     Pob
    -0.08
    æĮģç»ŃæıIJåįĩ
    -0.07
    zec
    -0.07
    çķĶ
    -0.07
    imak
    -0.07
    å°ĶåŁº
    -0.07
    haps
    -0.07
    kob
    -0.07
    iono
    -0.07
     mong
    -0.07
    POSITIVE LOGITS
    ä¸įæī¿æĭħä»»ä½ķ
    0.07
    witz
    0.07
     invisible
    0.07
    çŀij
    0.06
     comm
    0.06
    лиз
    0.06
    ä»Ģä¹Īéĥ½ä¸į
    0.06
    .documentElement
    0.06
    æķ´
    0.06
    éĢıæĺİ
    0.06
    Activations Density 0.004%

    No Known Activations