© 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. 16706
    Prev
    Next
    INDEX
    Explanations

    said it, expressing his, very clever

    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
    ç»Ļ对æĸ¹
    -0.08
    yczy
    -0.06
    人家
    -0.06
     unfortunate
    -0.06
    гоÑĢо
    -0.06
    对æĸ¹
    -0.06
    å¸Īå§IJ
    -0.06
     desperate
    -0.05
     entirety
    -0.05
     lite
    -0.05
    POSITIVE LOGITS
    кеÑĢ
    0.07
    cken
    0.06
    éļĪ
    0.06
     ev
    0.06
    agh
    0.05
    çĭIJ
    0.05
    azar
    0.05
    acen
    0.05
     getpid
    0.05
    åıĪå¤ļ
    0.05
    Activations Density 0.003%

    No Known Activations