© 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. 18641
    Prev
    Next
    INDEX
    Explanations

    **Font files and properties**

    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
    ergestellt
    -0.09
    ar
    -0.08
    rash
    -0.07
    ermann
    -0.07
    è´¥
    -0.07
     Renders
    -0.07
    rach
    -0.07
    isons
    -0.07
    ÄįÃŃ
    -0.07
    ió
    -0.07
    POSITIVE LOGITS
    à
    0.05
    wykle
    0.05
    å¤ĸåIJij
    0.05
    æ°£
    0.05
    سÙħ
    0.05
     trá»ĭ
    0.05
    ìļĶ
    0.05
     ìķĦëĭĪëĿ¼
    0.05
     volt
    0.05
    หลัà¸ĩ
    0.05
    Activations Density 0.008%

    No Known Activations