© 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. 21086
    Prev
    Next
    INDEX
    Explanations

    dates and names

    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
    滿滿
    -0.05
    å·¡
    -0.05
    ÙĥÙĦ
    -0.05
     denken
    -0.05
    عدÙħ
    -0.05
     Hogy
    -0.05
    æĭ¬
    -0.05
    è®Ńç»ĥä¸Ń
    -0.05
    以大
    -0.05
     cảnh
    -0.05
    POSITIVE LOGITS
    falls
    0.06
    æĺ¥ç§ĭ
    0.05
    ahl
    0.05
     finalmente
    0.05
    女足
    0.05
    Fall
    0.05
    åĬŀ主任
    0.05
    ÉĻn
    0.05
    à¸ķัว
    0.05
    ifer
    0.05
    Activations Density 0.083%

    No Known Activations