© 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. 34874
    Prev
    Next
    INDEX
    Explanations

    parameter names or identifiers

    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
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.07
    æį²
    -0.06
    èĦ«
    -0.06
    zkod
    -0.06
    èĦ±
    -0.06
    ëĭ¥
    -0.06
    виÑĤ
    -0.06
    缨
    -0.06
    ower
    -0.06
     REMOVE
    -0.06
    POSITIVE LOGITS
    ãĢįãĢģãĢĮ
    0.09
    )ãĢģ
    0.09
    ï¼īãĢģ
    0.08
    ãĢįãĢĮ
    0.08
    ãĢıãĢİ
    0.08
    ç©Į
    0.07
    åĴĮ西
    0.07
    羡
    0.07
    åĴĮåIJĦç§į
    0.07
    åIJĮçIJĨ
    0.07
    Activations Density 0.045%

    No Known Activations