© 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. 23073
    Prev
    Next
    INDEX
    Explanations

    sparse regularization

    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
    æĬ½ç©º
    -0.07
    é»ĦçīĽ
    -0.07
    betrieb
    -0.07
    è¿Ľè¡Įä¸Ģ次
    -0.06
    å¤ļ姿
    -0.06
    åĢĴéľī
    -0.06
    Unhandled
    -0.06
    æİĴåĩº
    -0.06
     Picker
    -0.06
    æĥĬéĻ©
    -0.06
    POSITIVE LOGITS
     regularization
    0.10
     penal
    0.09
    arsity
    0.09
    sparse
    0.09
    éĢ¼
    0.09
     Sparse
    0.09
    Sparse
    0.08
    anny
    0.08
     aggressively
    0.08
    vig
    0.08
    Activations Density 0.034%

    No Known Activations