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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19725
    Prev
    Next
    INDEX
    Explanations

    DM, GM, referee, master

    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
    ä¹ĭéķ¿
    -0.06
    ä¸įå½Ĵ
    -0.06
     adquis
    -0.05
     trup
    -0.05
    aho
    -0.05
    ikli
    -0.05
    ickey
    -0.05
    ah
    -0.05
    çļĦ人åijĺ
    -0.05
     ageing
    -0.05
    POSITIVE LOGITS
    lands
    0.06
    éļIJèĹıçļĦ
    0.06
    è¢į
    0.05
    reté
    0.05
    .FONT
    0.05
    iete
    0.05
    é¦ĸéĥ¨
    0.05
     lá»ĵ
    0.05
    Ä±ÅŁÄ±
    0.05
    ç§ĺ
    0.05
    Activations Density 0.001%

    No Known Activations