© 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. 19745
    Prev
    Next
    INDEX
    Explanations

    events occurring soon after

    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
    ibir
    -0.06
    认为
    -0.05
    entra
    -0.05
    rik
    -0.05
    ince
    -0.05
    çļĦä¸ĢçĶŁ
    -0.05
    lim
    -0.05
    etim
    -0.05
    ÑĢа
    -0.05
    ib
    -0.05
    POSITIVE LOGITS
     cristi
    0.06
    æ´ĭ
    0.06
     ÐļÑĢÑĸм
    0.06
    betul
    0.06
    Bearer
    0.06
    gnore
    0.06
    ä½łè·Ł
    0.05
    ãĥĩãĤ£ãĤ¹
    0.05
     SHALL
    0.05
    Cong
    0.05
    Activations Density 0.042%

    No Known Activations