© 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. 20906
    Prev
    Next
    INDEX
    Explanations

    famous

    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
    äºĨè¿Ļ个
    -0.07
    hil
    -0.07
    们çļĦ
    -0.07
    äºĨä»ĸçļĦ
    -0.07
    èĩ³æĸ¼
    -0.07
    uben
    -0.07
    们éĥ½
    -0.07
    avors
    -0.07
    äºĨæĪij们
    -0.07
    serrat
    -0.06
    POSITIVE LOGITS
    пÑı
    0.05
    ulates
    0.05
    .energy
    0.05
    reja
    0.05
    htag
    0.05
    новÑĮ
    0.05
    ait
    0.05
    धà¥Ģ
    0.05
    äºİ
    0.05
    ULATE
    0.05
    Activations Density 0.005%

    No Known Activations