© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21066
    Prev
    Next
    INDEX
    Explanations

    css position properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éķ¿æĪIJ
    -0.06
    ervi
    -0.06
     ÑĢода
    -0.06
    âĢ§
    -0.06
    rš
    -0.06
    åįĩæģ¯
    -0.06
     whoever
    -0.05
    annels
    -0.05
    çļĦä¸įæĺ¯
    -0.05
    à¸Ĺัà¹īà¸ĩ
    -0.05
    POSITIVE LOGITS
    游
    0.06
     menyemb
    0.05
    ÙĦاء
    0.05
    gon
    0.05
    ary
    0.05
    men
    0.05
    åĪĻåı¯ä»¥
    0.05
    ụt
    0.05
    å®ŀéªĮä¸ŃåѦ
    0.05
    sch
    0.05
    Activations Density 0.010%

    No Known Activations