© 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. 7295
    Prev
    Next
    INDEX
    Explanations

    connections, graphs, and links

    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
    blatt
    -0.07
    voir
    -0.07
    گذارÛĮ
    -0.07
    æĺ¯ä¸İ
    -0.07
    glas
    -0.07
    款çļĦ
    -0.07
    gerecht
    -0.07
    atur
    -0.07
     blunt
    -0.06
    illeurs
    -0.06
    POSITIVE LOGITS
    ness
    0.11
    ropy
    0.09
    éļĪ
    0.08
    keit
    0.08
    ieli
    0.07
     há»ĵn
    0.07
    irma
    0.07
    Ĺı
    0.07
    ity
    0.07
    иÑı
    0.07
    Activations Density 0.004%

    No Known Activations