© 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. 50774
    Prev
    Next
    INDEX
    Explanations

    Gafchromic, K, RE, thermography

    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
    um
    -0.07
    aint
    -0.07
    elor
    -0.07
    alt
    -0.06
    ovar
    -0.06
    ä¸ŃæĢ§
    -0.06
     derog
    -0.06
     Chill
    -0.06
    ul
    -0.06
    iz
    -0.06
    POSITIVE LOGITS
    WithData
    0.09
     progress
    0.09
     Sunrise
    0.08
    eru
    0.08
    клÑİ
    0.08
    亿åIJ¨
    0.08
    微波çĤī
    0.08
    progress
    0.07
    å¢ŀéĩı
    0.07
     Progress
    0.07
    Activations Density 0.003%

    No Known Activations