© 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. 20732
    Prev
    Next
    INDEX
    Explanations

    specific letter endings

    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
    Ord
    -0.06
     Ord
    -0.06
    ordin
    -0.05
    IVEN
    -0.05
    isto
    -0.05
    ↵↵
    -0.05
    åı¤ä»Ĭ
    -0.05
    åIJĮæł·
    -0.05
     ord
    -0.05
     аÑĢÑĤи
    -0.05
    POSITIVE LOGITS
     remont
    0.07
    æł¹æį®ä½łçļĦ
    0.06
    è§ģ人
    0.06
    лÑİби
    0.06
    ä¸ĵä¸ļåŃ¦æł¡
    0.06
     remise
    0.06
    entras
    0.06
    PHONE
    0.06
    aises
    0.06
    inya
    0.06
    Activations Density 0.056%

    No Known Activations