© 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. 18883
    Prev
    Next
    INDEX
    Explanations

    CORS Origin

    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
    าม
    -0.06
    ελ
    -0.06
    æg
    -0.06
    agraph
    -0.06
    ORES
    -0.05
    crow
    -0.05
     tess
    -0.05
    ÙĪصÙĦ
    -0.05
    åĤ¨èĹı
    -0.05
    é¹
    -0.05
    POSITIVE LOGITS
     patiently
    0.06
    nable
    0.06
    æİĪ
    0.06
    puter
    0.06
     proposition
    0.06
     pasaj
    0.05
    ب
    0.05
    جاÙĨ
    0.05
    ille
    0.05
    ÑĢон
    0.05
    Activations Density 0.003%

    No Known Activations