© 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. 58798
    Prev
    Next
    INDEX
    Explanations

    masking and programming contexts

    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
    gnore
    -0.08
     handful
    -0.08
    好å¤ĦçļĦ
    -0.08
    thouse
    -0.07
    orten
    -0.07
    iday
    -0.07
    ArrayOf
    -0.07
    leÅŁ
    -0.07
    eger
    -0.07
    umph
    -0.07
    POSITIVE LOGITS
    ingly
    0.10
    ä¸įä½ıçļĦ
    0.08
    andinav
    0.08
    otte
    0.08
    ierung
    0.08
    aroo
    0.08
    edTextBox
    0.08
    edException
    0.08
    ï¼Ŀï¼Ŀï¼Ŀï¼Ŀ
    0.07
    ellaneous
    0.07
    Activations Density 0.013%

    No Known Activations