© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22602
    Prev
    Next
    INDEX
    Explanations

    various combinations/sequences

    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
    Negative Logits
    us
    -0.05
    è¿İ
    -0.05
    emaakt
    -0.05
    ÑģÑĤÑĢÑĥк
    -0.05
    è£Ĥ
    -0.05
    éĩĮçļĦ
    -0.05
    ä¾ĭè¡Į
    -0.05
    ç»ĵæŀĦ
    -0.05
    structure
    -0.05
    ollen
    -0.05
    POSITIVE LOGITS
     combinations
    0.08
    æł¹æį®ä¸įåIJĮ
    0.07
     combos
    0.07
     kombinasi
    0.06
    ä¸ĭå®ļ
    0.06
     Kombin
    0.06
    æĬĦåºķ
    0.06
     varied
    0.06
    æłĩåĩĨä¿¡æģ¯
    0.06
    katan
    0.06
    Activations Density 0.071%

    No Known Activations