© 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. 17527
    Prev
    Next
    INDEX
    Explanations

    `id` attribute values

    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
    á»ĩt
    -0.05
    ÄįetnÄĽ
    -0.05
    "
    -0.05
     паÑĢа
    -0.05
    returns
    -0.05
    à¸ı
    -0.05
    åĩºèĩª
    -0.05
    è¾¾
    -0.05
     padded
    -0.05
    èµIJ
    -0.05
    POSITIVE LOGITS
    ’B
    0.06
    絡
    0.05
    ENDER
    0.05
    λί
    0.05
    андÑĢ
    0.05
    asia
    0.05
    æıIJçIJ´
    0.05
    éħįæħ®
    0.05
    ëĿ½ìĿĦ
    0.05
    Spaces
    0.05
    Activations Density 0.038%

    No Known Activations