© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11696
    Prev
    Next
    INDEX
    Explanations

    advertising, day, exception, place, States, sound, arena, music

    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
    ...,
    -0.07
      ↵↵↵
    -0.06
    );}
    -0.06
    ↵↵    ↵
    -0.06
     ?,
    -0.06
    .tw
    -0.06
     ?",
    -0.06
    é¸ŃèĽĭ
    -0.06
    imd
    -0.06
    ä¸īåı£
    -0.06
    POSITIVE LOGITS
    èĮģ
    0.09
    ãĢĤãĢĮ
    0.09
    ãĢĤ
    0.08
    ëĭ¤
    0.08
    ç«ĭä¿¡
    0.07
    +_
    0.07
    rieb
    0.07
    ãĢĤ“
    0.07
    ë¥Ń
    0.07
    -disabled
    0.07
    Activations Density 0.353%

    No Known Activations