© 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. 32540
    Prev
    Next
    INDEX
    Explanations

    sequences involving sums and limits

    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
    regor
    -0.07
     sor
    -0.07
    aland
    -0.07
     ÑĤеÑħни
    -0.07
    æī©å±ķèµĦæĸĻ
    -0.07
    å°±çŁ¥éģĵ
    -0.07
    åĮĹæ±½
    -0.07
     descont
    -0.07
    ordo
    -0.06
    è°¨
    -0.06
    POSITIVE LOGITS
    éĿĴ天
    0.07
    unders
    0.07
    $$
    0.07
     Grie
    0.07
    odne
    0.07
    icule
    0.06
    vÄĥ
    0.06
    izioni
    0.06
    ogos
    0.06
    -begin
    0.06
    Activations Density 0.085%

    No Known Activations