© 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. 19548
    Prev
    Next
    INDEX
    Explanations

    punctuation, sentence termination

    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
    ç¥Ģ
    -0.06
    exact
    -0.06
     dil
    -0.06
    olina
    -0.06
    ons
    -0.05
     fram
    -0.05
    ollo
    -0.05
    èģĶç³»
    -0.05
     MS
    -0.05
    è¾¾æĸ¯
    -0.05
    POSITIVE LOGITS
    ip
    0.06
    æ£Ģå¯Łéķ¿
    0.06
    ãģ«è¡Įãģ£ãģ¦ãģįãģ¾ãģĹãģŁ
    0.05
    æĥħåĨµè¿Ľè¡ĮäºĨ
    0.05
    年以ä¸ĭ
    0.05
     вообÑĢа
    0.05
    客製
    0.05
    ãģ£ãģ¦ãģ¿ãģ¾ãģĹãģŁ
    0.05
    ipe
    0.05
    ounters
    0.05
    Activations Density 0.003%

    No Known Activations