© 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. 20727
    Prev
    Next
    INDEX
    Explanations

    flowers

    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
    ergarten
    -0.07
    ungkapkan
    -0.07
    -0.07
    à¤ľà¥įà¤ŀ
    -0.07
    ä¸įè¦ģ被
    -0.07
    ابÛĮ
    -0.07
    nad
    -0.07
    ÑİÑĤ
    -0.07
    äºĨ大éĩı
    -0.07
    лÑİд
    -0.06
    POSITIVE LOGITS
    er
    0.07
    ities
    0.06
    ishes
    0.06
    ../../../
    0.05
    king
    0.05
    ilities
    0.05
    е
    0.05
    ãģįãģ¦
    0.05
     latter
    0.05
     Beat
    0.05
    Activations Density 0.005%

    No Known Activations