© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12102
    Prev
    Next
    INDEX
    Explanations

    footballer or player

    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
     اÙĦÙħÙģت
    -0.07
    æ¯Ķäºļ
    -0.07
    æĪijçļĦå¿ĥæĥħ
    -0.07
     ÙħÙģت
    -0.07
     geometr
    -0.07
    ünd
    -0.07
    amid
    -0.06
    acken
    -0.06
    ffit
    -0.06
    -AA
    -0.06
    POSITIVE LOGITS
    主页
    0.08
    mania
    0.07
    ä¸ĩåĽ½
    0.07
    idou
    0.07
    ç»ĪçĶŁ
    0.06
    innen
    0.06
    å¤ļ大
    0.06
    港åı£
    0.06
    itate
    0.06
    -export
    0.06
    Activations Density 0.151%

    No Known Activations