© 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. 21985
    Prev
    Next
    INDEX
    Explanations

    "unities"

    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
    à¹Ĥà¸Ĺษ
    -0.05
    æħ¶
    -0.05
    inste
    -0.05
    سات
    -0.05
    æĺ¯ä¸Ģç§įéĿŀ常
    -0.05
    ursors
    -0.05
     sobres
    -0.05
    æĮ¨
    -0.05
    -way
    -0.05
    iors
    -0.05
    POSITIVE LOGITS
    otto
    0.06
    atz
    0.06
    mong
    0.05
    one
    0.05
    ood
    0.05
    abat
    0.05
    affe
    0.05
    setMax
    0.05
    çĿĽ
    0.05
    ario
    0.05
    Activations Density 0.005%

    No Known Activations