© 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. 17902
    Prev
    Next
    INDEX
    Explanations

    storage and preservation

    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
     secrecy
    -0.07
    us
    -0.07
     Powers
    -0.07
    èº
    -0.07
    aré
    -0.06
     Venture
    -0.06
    acular
    -0.06
    à¹ģà¸Ŀ
    -0.06
    Power
    -0.06
    ä¼ģä¸ļç»ıèIJ¥
    -0.06
    POSITIVE LOGITS
    ä¸ŃæĢ§
    0.09
     Aerop
    0.08
    lette
    0.08
    顺åħ¶èĩªçĦ¶
    0.08
     portav
    0.07
    èŤ
    0.07
    Sdk
    0.07
    utati
    0.07
    eggi
    0.07
    米
    0.07
    Activations Density 0.012%

    No Known Activations