© 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. 35063
    Prev
    Next
    INDEX
    Explanations

    file paths and codes

    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
    ÚĺÙĩ
    -0.07
    is
    -0.06
     maintained
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    à¯įதà¯įத
    -0.06
    .
    -0.06
    TURE
    -0.05
    emes
    -0.05
    OMET
    -0.05
    otypical
    -0.05
    POSITIVE LOGITS
    åįļä¼ļ
    0.08
    gelig
    0.08
    idé
    0.08
    æłijä¸Ģ
    0.08
    icité
    0.08
    enal
    0.08
    âĢ¦âĢ¦ãĢĤ
    0.07
    lÉĻÅŁ
    0.07
    ewis
    0.07
     orto
    0.07
    Activations Density 0.119%

    No Known Activations