© 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. 19498
    Prev
    Next
    INDEX
    Explanations

    when

    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
    essin
    -0.08
    ئÙĩ
    -0.07
    ornado
    -0.07
    Å¡ti
    -0.07
    urun
    -0.07
    endu
    -0.06
     mutl
    -0.06
     sufici
    -0.06
    çļĦæ©Łæľĥ
    -0.06
    çļĦéĥ½
    -0.06
    POSITIVE LOGITS
     lo
    0.05
    lin
    0.05
    æĦıåij³çĿĢ
    0.05
    ↵↵
    0.05
     sap
    0.05
    并ä¸įæĺ¯
    0.05
    并éĿŀ
    0.05
    0.05
     seed
    0.05
     sign
    0.05
    Activations Density 0.031%

    No Known Activations