© 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. 19884
    Prev
    Next
    INDEX
    Explanations

    code delimiters and structure

    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
    ارة
    -0.07
    ooth
    -0.06
    å¼ı设计
    -0.06
    chera
    -0.06
    arau
    -0.06
    iture
    -0.06
    èĦ¯
    -0.06
    elok
    -0.06
     emozion
    -0.06
    rej
    -0.06
    POSITIVE LOGITS
     bis
    0.06
    èĦ±
    0.05
    æ°ij
    0.05
     rather
    0.05
    æ´»
    0.05
    ocha
    0.05
    èĢĮéĿŀ
    0.05
     ell
    0.05
    ä¸ĩå¹´
    0.05
    ç«ĭ
    0.05
    Activations Density 0.014%

    No Known Activations