© 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. 34943
    Prev
    Next
    INDEX
    Explanations

    infimum and supremum

    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
    illi
    -0.07
     prepared
    -0.07
    äºļè¿IJ
    -0.06
    ânia
    -0.06
    Wildcard
    -0.06
    为åģļ好
    -0.06
    achs
    -0.06
    她表示
    -0.06
    aho
    -0.06
    chal
    -0.06
    POSITIVE LOGITS
    imum
    0.08
    imize
    0.08
    uger
    0.07
    诸
    0.07
    _EXIST
    0.07
    imal
    0.07
     among
    0.07
    æ°´æ´Ĺ
    0.07
    petto
    0.07
    lise
    0.07
    Activations Density 0.002%

    No Known Activations