© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17625
    Prev
    Next
    INDEX
    Explanations

    file extensions

    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
    åłª
    -0.06
    æ°Ķåij³
    -0.05
    inst
    -0.05
     ìľ¡
    -0.05
     kun
    -0.05
    åŃĺ
    -0.05
     skr
    -0.05
    ÙĪØ®
    -0.05
    ouvrez
    -0.05
    run
    -0.05
    POSITIVE LOGITS
    atab
    0.06
    инÑĥ
    0.06
    缸åħ³è¦ģæ±Ĥ
    0.06
    appa
    0.06
    à¸łà¸²à¸ŀ
    0.06
    ones
    0.06
    athom
    0.06
    æĽ´åĬłæĸ¹ä¾¿
    0.06
    ders
    0.06
    æľīæį®
    0.06
    Activations Density 0.001%

    No Known Activations