© 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. 16674
    Prev
    Next
    INDEX
    Explanations

    create from

    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
    æ¦Ķ
    -0.06
    orado
    -0.06
    ÄĽr
    -0.06
    ques
    -0.06
    ples
    -0.05
     prem
    -0.05
    å¢ħ
    -0.05
     Modeling
    -0.05
    tud
    -0.05
    жаем
    -0.05
    POSITIVE LOGITS
    st
    0.06
    Ñĥ
    0.05
    æľīæŶ
    0.05
    obb
    0.05
    duct
    0.05
    prise
    0.05
    z
    0.05
    mploy
    0.05
    yectos
    0.05
    engah
    0.05
    Activations Density 0.029%

    No Known Activations