© 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. 22277
    Prev
    Next
    INDEX
    Explanations

    names followed by names, possessives, or verbs

    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
    éĤ£èĤ¡
    -0.06
    éĤ£ä»½
    -0.05
    è¿Ļ份
    -0.05
    ingue
    -0.05
    ä¹Ŀé¾Ļ
    -0.05
    ÙĬض
    -0.05
    éĤ£å¼ł
    -0.05
    æĮ½
    -0.05
    åıªçľĭ
    -0.05
    å¸ĥ
    -0.05
    POSITIVE LOGITS
     starting
    0.06
    amanya
    0.06
    è£Ĥ
    0.06
    ç³Ļ
    0.06
    ÄĻż
    0.06
    roits
    0.05
     дÑĢÑĥг
    0.05
    ovski
    0.05
    EXT
    0.05
    [opt
    0.05
    Activations Density 0.019%

    No Known Activations