© 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. 16560
    Prev
    Next
    INDEX
    Explanations

    artist biographies and descriptions

    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
    lesi
    -0.08
    lege
    -0.07
    loon
    -0.06
    resp
    -0.06
    ../../../
    -0.06
    ä»Ģä¹Īåij¢
    -0.06
    nish
    -0.06
     antaranya
    -0.06
    wards
    -0.06
    stin
    -0.06
    POSITIVE LOGITS
    æł·çļĦ
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.07
    gether
    0.07
    haft
    0.06
    ate
    0.06
    fle
    0.06
    ê»ĺ
    0.06
    ä¼Łå¤§çļĦ
    0.06
    emble
    0.06
    ложенÑĭ
    0.06
    Activations Density 0.016%

    No Known Activations