© 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. 17962
    Prev
    Next
    INDEX
    Explanations

    pool

    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
    aped
    -0.06
    icat
    -0.06
    opak
    -0.06
    emes
    -0.06
    ãģĦãģĨ
    -0.06
    å¾ĢæľŁç²¾å½©
    -0.06
    emis
    -0.06
    ا
    -0.06
    æĪIJä¸Ģ
    -0.06
     kalinya
    -0.06
    POSITIVE LOGITS
    룬
    0.08
    ê²ĥìĿ´
    0.06
    ased
    0.06
    cock
    0.06
    ì¦ĿìĿĦ
    0.06
    æ±ł
    0.06
     expended
    0.06
    à¸Ķิà¸ļ
    0.06
    次çļĦ
    0.06
    éĢļè¿ĩ对
    0.05
    Activations Density 0.014%

    No Known Activations