© 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. 17277
    Prev
    Next
    INDEX
    Explanations

    board game

    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
    UC
    -0.05
    äººæł¼
    -0.05
    pear
    -0.05
    '
    -0.05
    orph
    -0.05
    ved
    -0.05
    .cat
    -0.05
    fulness
    -0.05
    个人
    -0.05
    æĵį纵
    -0.05
    POSITIVE LOGITS
    gege
    0.07
    ç§ijåѦçłĶ究éĻ¢
    0.07
    åħ¬åĭŁ
    0.06
     siège
    0.06
    åĮĹåIJij
    0.06
    éĶĻé¢ĺ
    0.06
    avia
    0.06
    éľīç´ł
    0.06
    丹
    0.06
    amente
    0.06
    Activations Density 0.006%

    No Known Activations