© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18966
    Prev
    Next
    INDEX
    Explanations

    US Court Appeals

    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
    à¸Ĺีà¹Īà¸ķัà¹īà¸ĩ
    -0.06
    书记
    -0.06
    oved
    -0.06
    ä¸įåİĮ
    -0.05
     Presup
    -0.05
    èģ
    -0.05
    HQ
    -0.05
    ÄĻp
    -0.05
     bios
    -0.05
     realtime
    -0.05
    POSITIVE LOGITS
    lene
    0.05
    tele
    0.05
     Gim
    0.05
     subs
    0.05
    esser
    0.05
     pie
    0.05
    æ¶īå«Į
    0.05
    ака
    0.05
    immers
    0.05
    icat
    0.05
    Activations Density 0.019%

    No Known Activations