© 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. 12325
    Prev
    Next
    INDEX
    Explanations

    license and commercial usage

    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
     almost
    -0.08
    åĩłä¹İ
    -0.07
    åĩłä¹İæĺ¯
    -0.07
    almost
    -0.07
    ä¸į太好
    -0.07
    ãģĻãģĮ
    -0.07
    ±
    -0.07
    ouri
    -0.06
    åı¯æĥľ
    -0.06
    ç¾İä¸Ń
    -0.06
    POSITIVE LOGITS
     appropriate
    0.10
    ä¸ĵéŨçļĦ
    0.10
    appropriate
    0.10
     надлежа
    0.10
    缸åºĶçļĦ
    0.09
     appropriately
    0.09
     approved
    0.09
    ä¸ĵçĶ¨çļĦ
    0.09
     ÙħخصÙĪص
    0.09
     specially
    0.09
    Activations Density 0.094%

    No Known Activations