© 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. 44807
    Prev
    Next
    INDEX
    Explanations

    @page parser

    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
    utory
    -0.09
     Gabin
    -0.08
    èĤļ
    -0.08
    urare
    -0.07
    ÙĪÛĮÙĩ
    -0.07
    Ìģ
    -0.07
    è·¯ä¸ľ
    -0.07
     вÑģÑı
    -0.07
    .cm
    -0.07
    ارب
    -0.07
    POSITIVE LOGITS
    åĪ«è¯´
    0.07
    ListOf
    0.07
    ؤÙĦ
    0.07
    ORTE
    0.06
    æľĽ
    0.06
    ç»į
    0.06
    å¤ļæĥħ
    0.06
    expo
    0.06
    owering
    0.06
    oble
    0.06
    Activations Density 0.002%

    No Known Activations