© 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. 22432
    Prev
    Next
    INDEX
    Explanations

    virus, iphere, ercial, atria

    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
    è¾¾æĭī
    -0.05
    R
    -0.05
     frank
    -0.05
    G
    -0.05
    çŀĴ
    -0.05
    -thinking
    -0.05
     боле
    -0.05
    Ø°Ùĥ
    -0.05
    iliar
    -0.05
     genug
    -0.04
    POSITIVE LOGITS
    ebbe
    0.07
    ÃĹ</
    0.07
    üb
    0.06
    ãĢij,
    0.06
    çĤ¹åĦ¿
    0.06
    漿
    0.06
     sót
    0.06
     Fons
    0.06
    atria
    0.06
    .en
    0.06
    Activations Density 0.325%

    No Known Activations