© 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. 39687
    Prev
    Next
    INDEX
    Explanations

    Eastern, Pacific, UK, ET times

    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
    sla
    -0.08
     sekali
    -0.08
    请çľĭ
    -0.07
    ä¹ĿéľĦ
    -0.07
    个个
    -0.07
    etting
    -0.07
    nika
    -0.07
    หà¸Ļà¹Īà¸Ńย
    -0.07
    akit
    -0.07
    æľįåĬ¡å¯¹è±¡
    -0.07
    POSITIVE LOGITS
     기ì¤Ģ
    0.07
     equivalent
    0.06
    edly
    0.06
    ลà¹ĩ
    0.06
    기ì¤Ģ
    0.06
    -buttons
    0.06
     cosa
    0.06
     기ì¤Ģìľ¼ë¡ľ
    0.06
    ukai
    0.06
    à¹Īาว
    0.06
    Activations Density 0.083%

    No Known Activations