© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37572
    Prev
    Next
    INDEX
    Explanations

    remainder calculation

    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
    Negative Logits
    opa
    -0.08
    ä¸īéĢļ
    -0.07
    åĽ½å¼º
    -0.07
    uellen
    -0.06
    ology
    -0.06
    urah
    -0.06
    stein
    -0.06
    zon
    -0.06
    æĦ§
    -0.06
     balloon
    -0.06
    POSITIVE LOGITS
     antif
    0.08
    çļĦåıį
    0.08
     equival
    0.08
    åĮķ
    0.08
     anti
    0.07
     equivalent
    0.07
    娲
    0.07
     antagon
    0.07
    akra
    0.07
    .reverse
    0.07
    Activations Density 0.003%

    No Known Activations