© 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. 22501
    Prev
    Next
    INDEX
    Explanations

    working with

    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
    vo
    -0.06
    '%
    -0.06
    ä¸İ被
    -0.06
    [âĢ¦
    -0.06
    (IR
    -0.05
    ç´§è¦ģ
    -0.05
    (Int
    -0.05
    管æĬ¤
    -0.05
    åıĤä¸İæ´»åĬ¨
    -0.05
    edio
    -0.05
    POSITIVE LOGITS
    åĴĮåĬªåĬĽ
    0.07
    ingly
    0.06
    ×ļ
    0.06
    ç³»ç»Łè¿Ľè¡Į
    0.06
    idão
    0.06
    ساÙħ
    0.06
    žel
    0.05
    çİ°è¡ĮçļĦ
    0.05
    гаÑĤо
    0.05
    Ñĩиной
    0.05
    Activations Density 0.017%

    No Known Activations