© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18671
    Prev
    Next
    INDEX
    Explanations

    policy and rates

    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
    Not in Any Lists

    No Comments

    Negative Logits
     des
    -0.05
     rec
    -0.05
    års
    -0.05
    à¹ģà¸ľà¸Ļ
    -0.04
    æ´»è·ĥçļĦ
    -0.04
     bás
    -0.04
    æ¼Ĥ
    -0.04
    Õ¡Õ£
    -0.04
     fed
    -0.04
    èĢĮä¸į
    -0.04
    POSITIVE LOGITS
    oter
    0.06
    endió
    0.06
    unic
    0.06
    èĭijå°ıåĮº
    0.06
    解å°ģ
    0.06
    evel
    0.06
    estig
    0.06
    reek
    0.06
    ÑĤÑĸм
    0.06
    eau
    0.06
    Activations Density 0.001%

    No Known Activations