© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19562
    Prev
    Next
    INDEX
    Explanations

    special characters

    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
     det
    -0.06
     inf
    -0.06
     term
    -0.05
    det
    -0.05
    term
    -0.05
    æĪijè·Ł
    -0.05
     pit
    -0.05
    æĸ¼
    -0.05
    ä½Ļ人次
    -0.05
    _traits
    -0.05
    POSITIVE LOGITS
    ä»Ģä¹Īéĥ½
    0.07
    oret
    0.06
     closest
    0.06
    طار
    0.06
    orean
    0.06
     finest
    0.06
    æľĢä½³
    0.06
    æľĢ好
    0.06
     democ
    0.05
     Pfeffer
    0.05
    Activations Density 0.003%

    No Known Activations