© 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. 16765
    Prev
    Next
    INDEX
    Explanations

    command line arguments (argv)

    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
    gre
    -0.06
    PACK
    -0.05
    LONG
    -0.05
    erview
    -0.05
    inue
    -0.05
    eneral
    -0.05
    ult
    -0.05
    æĬĺä¸į
    -0.05
    .Wrap
    -0.05
    unsigned
    -0.05
    POSITIVE LOGITS
    illen
    0.07
    缸åºĶ
    0.06
    anat
    0.06
    aed
    0.06
    adel
    0.06
    isations
    0.06
    etem
    0.06
    uais
    0.06
    aisons
    0.06
    ÑĤик
    0.06
    Activations Density 0.005%

    No Known Activations