© 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. 47120
    Prev
    Next
    INDEX
    Explanations

    import or open preceding code constructs

    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
    ilon
    -0.08
    egend
    -0.07
    ount
    -0.07
    à¸Ĺุà¹Īม
    -0.07
    ī
    -0.07
    æĹ¥å¤ľ
    -0.07
    ä»Ģ
    -0.07
    ä¸ĭèį¯
    -0.07
    æĪijæ¯ı天
    -0.07
    çľ¼è§ģ
    -0.07
    POSITIVE LOGITS
    èĽĭ
    0.07
    æĺŁæ²³
    0.07
    elman
    0.06
    ¦
    0.06
    ç½ijä¸Ĭ
    0.06
    ETS
    0.06
    丽人
    0.06
    æľĢæĸ°
    0.06
    _once
    0.06
    scratch
    0.06
    Activations Density 0.004%

    No Known Activations