© 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. 17454
    Prev
    Next
    INDEX
    Explanations

    great time

    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
     ÑĤаки
    -0.07
    mond
    -0.07
    imon
    -0.06
    uable
    -0.06
    udin
    -0.06
    ť
    -0.06
    åĵģçļĦ
    -0.06
    Ñijл
    -0.06
    ìļĶ
    -0.06
    uden
    -0.06
    POSITIVE LOGITS
    æł¹æľ¬ä¸Ĭ
    0.06
    ea
    0.06
    gether
    0.06
    be
    0.05
     prosp
    0.05
    place
    0.05
     tind
    0.05
    عÙĦÙĨت
    0.05
    liness
    0.05
    broken
    0.05
    Activations Density 0.003%

    No Known Activations