© 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. 61716
    Prev
    Next
    INDEX
    Explanations

    creating instances

    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
    habi
    -0.07
    upu
    -0.07
    ihal
    -0.07
    软件ä¸ĭè½½
    -0.07
    .rmi
    -0.07
    icz
    -0.07
    广è§Ĵ
    -0.06
    ouse
    -0.06
    wyn
    -0.06
    ×Ĺ×Ļ
    -0.06
    POSITIVE LOGITS
    åıªä»£è¡¨
    0.10
     whose
    0.09
     ÑįкземплÑı
    0.09
     Ñįкзем
    0.09
     constructor
    0.09
     instance
    0.08
    å®ŀä¾ĭ
    0.08
     instantiation
    0.08
     initialized
    0.08
     creation
    0.08
    Activations Density 0.121%

    No Known Activations