© 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. 22625
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    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
     consultez
    -0.07
    nelle
    -0.06
    ,ep
    -0.06
    ãĤ¢ãĥ¡
    -0.06
    ãĤ»
    -0.06
    æĹłèĢ»
    -0.06
    elor
    -0.06
    ihar
    -0.06
    ÑģÑĤе
    -0.06
     rând
    -0.06
    POSITIVE LOGITS
    ark
    0.06
    ut
    0.06
    anto
    0.05
    T
    0.05
    è¿Ļä¸ĢçĤ¹
    0.05
    ot
    0.05
    at
    0.05
    TR
    0.05
    anti
    0.05
    r
    0.05
    Activations Density 0.294%

    No Known Activations