© 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. 46231
    Prev
    Next
    INDEX
    Explanations

    Dallas Mavericks

    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
    â
    -0.08
    illi
    -0.07
    å¾Ĺè¿ĩ
    -0.07
    oz
    -0.06
    âĢ
    -0.06
     Err
    -0.06
    /column
    -0.06
    ÃĤ
    -0.06
    ensch
    -0.06
    qx
    -0.06
    POSITIVE LOGITS
    adin
    0.09
    ãģ®ãģĭãĤĤãģĹãĤĮ
    0.08
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    0.08
    InParameter
    0.08
    GenerationStrategy
    0.07
    metros
    0.07
    ÙĪÛĮت
    0.07
    CREMENT
    0.07
    è·ĥè·ĥ欲è¯ķ
    0.07
     ÐIJпÑĢе
    0.07
    Activations Density 0.006%

    No Known Activations